Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4983 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.6137. Min Act: -0.1700
Data Index: 7605849 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.6137. Min Act: -0.1700
Data Index: 2284807 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.5824. Min Act: -0.1700
Data Index: 805989 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.5512. Min Act: -0.1700
Data Index: 1273249 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.5512. Min Act: -0.1700
Data Index: 3501693 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.4574. Min Act: -0.1700
Data Index: 5388041 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.3949. Min Act: -0.1700
Data Index: 3917998 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.3949. Min Act: -0.1700
Data Index: 20396 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.3012. Min Act: -0.1700
Data Index: 532624 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.2387. Min Act: -0.1700
Data Index: 6546389 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.2074. Min Act: -0.1700
Data Index: 950081 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.2387. Min Act: -0.1700
Data Index: 6834371 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.2387. Min Act: -0.1700
Data Index: 1442021 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.1762. Min Act: -0.1700
Data Index: 5388050 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.2074. Min Act: -0.1700
Data Index: 3738618 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.1449. Min Act: -0.1700
Data Index: 8692584 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.1449. Min Act: -0.1700
Data Index: 4244716 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.1449. Min Act: -0.1700
Data Index: 5297015 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.1137. Min Act: -0.1700
Data Index: 5533587 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6137. Min Range: -5.6137
Max Act: 5.0824. Min Act: -0.1700
Data Index: 4390298 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19