Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1256 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1443. Min Range: -5.1443
Max Act: 5.1130. Min Act: -0.1700
Data Index: 149378 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1443. Min Range: -5.1443
Max Act: 5.1443. Min Act: -0.1700
Data Index: 1067165 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1443. Min Range: -5.1443
Max Act: 5.1130. Min Act: -0.1699
Data Index: 370928 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1443. Min Range: -5.1443
Max Act: 5.1130. Min Act: -0.1700
Data Index: 4557488 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1443. Min Range: -5.1443
Max Act: 5.0818. Min Act: -0.1700
Data Index: 194549 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1443. Min Range: -5.1443
Max Act: 4.9880. Min Act: -0.1700
Data Index: 1625452 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1443. Min Range: -5.1443
Max Act: 5.0193. Min Act: -0.1700
Data Index: 3720639 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1443. Min Range: -5.1443
Max Act: 5.0193. Min Act: -0.1700
Data Index: 61300 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1443. Min Range: -5.1443
Max Act: 4.9880. Min Act: -0.1700
Data Index: 2573125 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1443. Min Range: -5.1443
Max Act: 5.0193. Min Act: -0.1700
Data Index: 5183642 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1443. Min Range: -5.1443
Max Act: 4.9568. Min Act: -0.1700
Data Index: 8799958 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1443. Min Range: -5.1443
Max Act: 4.9568. Min Act: -0.1700
Data Index: 2037831 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1443. Min Range: -5.1443
Max Act: 4.9568. Min Act: -0.1700
Data Index: 328145 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1443. Min Range: -5.1443
Max Act: 4.9255. Min Act: -0.1700
Data Index: 4241179 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1443. Min Range: -5.1443
Max Act: 4.9255. Min Act: -0.1700
Data Index: 3010041 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1443. Min Range: -5.1443
Max Act: 4.9255. Min Act: -0.1700
Data Index: 291450 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1443. Min Range: -5.1443
Max Act: 4.9255. Min Act: -0.1700
Data Index: 2394668 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1443. Min Range: -5.1443
Max Act: 4.9255. Min Act: -0.1700
Data Index: 4675102 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1443. Min Range: -5.1443
Max Act: 4.9255. Min Act: -0.1700
Data Index: 962939 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1443. Min Range: -5.1443
Max Act: 4.9255. Min Act: -0.1700
Data Index: 2455986 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19