Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3860 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1097. Min Range: -11.1097
Max Act: 11.1097. Min Act: -0.1700
Data Index: 6759217 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1097. Min Range: -11.1097
Max Act: 11.1097. Min Act: -0.1700
Data Index: 6458013 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1097. Min Range: -11.1097
Max Act: 11.0472. Min Act: -0.1700
Data Index: 3207429 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1097. Min Range: -11.1097
Max Act: 11.0472. Min Act: -0.1700
Data Index: 6797866 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1097. Min Range: -11.1097
Max Act: 11.0472. Min Act: -0.1700
Data Index: 8336120 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1097. Min Range: -11.1097
Max Act: 10.9847. Min Act: -0.1700
Data Index: 8157882 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1097. Min Range: -11.1097
Max Act: 10.9222. Min Act: -0.1700
Data Index: 4087606 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1097. Min Range: -11.1097
Max Act: 10.9222. Min Act: -0.1700
Data Index: 117474 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1097. Min Range: -11.1097
Max Act: 10.9222. Min Act: -0.1700
Data Index: 1336515 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1097. Min Range: -11.1097
Max Act: 10.9222. Min Act: -0.1700
Data Index: 3382280 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1097. Min Range: -11.1097
Max Act: 10.8597. Min Act: -0.1700
Data Index: 8650324 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1097. Min Range: -11.1097
Max Act: 10.8597. Min Act: -0.1700
Data Index: 5619502 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1097. Min Range: -11.1097
Max Act: 10.7972. Min Act: -0.1700
Data Index: 8650323 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1097. Min Range: -11.1097
Max Act: 10.8597. Min Act: -0.1700
Data Index: 3030086 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1097. Min Range: -11.1097
Max Act: 10.7972. Min Act: -0.1700
Data Index: 5073849 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1097. Min Range: -11.1097
Max Act: 10.7972. Min Act: -0.1700
Data Index: 4824549 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1097. Min Range: -11.1097
Max Act: 10.7347. Min Act: -0.1700
Data Index: 8799871 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1097. Min Range: -11.1097
Max Act: 10.7347. Min Act: -0.1700
Data Index: 6950528 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1097. Min Range: -11.1097
Max Act: 10.7347. Min Act: -0.1700
Data Index: 1720912 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1097. Min Range: -11.1097
Max Act: 10.6722. Min Act: -0.1700
Data Index: 669488 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19