Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3194 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.9842. Min Act: -0.1700
Data Index: 8361392 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.7967. Min Act: -0.1700
Data Index: 8470799 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.4217. Min Act: -0.1700
Data Index: 4981598 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.4217. Min Act: -0.1700
Data Index: 2687210 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.3592. Min Act: -0.1700
Data Index: 3987224 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.3592. Min Act: -0.1700
Data Index: 6454082 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.3279. Min Act: -0.1700
Data Index: 5349454 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.3279. Min Act: -0.1700
Data Index: 4930562 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.3279. Min Act: -0.1700
Data Index: 19538 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.2967. Min Act: -0.1700
Data Index: 1384955 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.3279. Min Act: -0.1700
Data Index: 2522200 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.2342. Min Act: -0.1700
Data Index: 1344355 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.2342. Min Act: -0.1700
Data Index: 2388578 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.2029. Min Act: -0.1700
Data Index: 7196513 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.1717. Min Act: -0.1700
Data Index: 8405072 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.1717. Min Act: -0.1700
Data Index: 6074695 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.1404. Min Act: -0.1700
Data Index: 5874385 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.1717. Min Act: -0.1700
Data Index: 8494109 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.1717. Min Act: -0.1700
Data Index: 2923549 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9842. Min Range: -4.9842
Max Act: 4.1717. Min Act: -0.1700
Data Index: 8248899 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19