Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1707 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1443. Min Range: -6.1443
Max Act: 6.1443. Min Act: -0.1700
Data Index: 8777251 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1443. Min Range: -6.1443
Max Act: 6.1130. Min Act: -0.1700
Data Index: 8045654 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1443. Min Range: -6.1443
Max Act: 6.1130. Min Act: -0.1700
Data Index: 6200636 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1443. Min Range: -6.1443
Max Act: 6.1130. Min Act: -0.1700
Data Index: 8699010 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1443. Min Range: -6.1443
Max Act: 6.1130. Min Act: -0.1700
Data Index: 2243377 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1443. Min Range: -6.1443
Max Act: 6.0193. Min Act: -0.1700
Data Index: 2035209 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1443. Min Range: -6.1443
Max Act: 5.9880. Min Act: -0.1700
Data Index: 6157349 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1443. Min Range: -6.1443
Max Act: 6.0505. Min Act: -0.1700
Data Index: 4148276 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1443. Min Range: -6.1443
Max Act: 6.0193. Min Act: -0.1700
Data Index: 2886010 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1443. Min Range: -6.1443
Max Act: 5.9880. Min Act: -0.1700
Data Index: 6871402 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1443. Min Range: -6.1443
Max Act: 5.9568. Min Act: -0.1700
Data Index: 7014679 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1443. Min Range: -6.1443
Max Act: 5.9568. Min Act: -0.1700
Data Index: 4040900 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1443. Min Range: -6.1443
Max Act: 5.9568. Min Act: -0.1700
Data Index: 519332 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1443. Min Range: -6.1443
Max Act: 5.9568. Min Act: -0.1700
Data Index: 7903456 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1443. Min Range: -6.1443
Max Act: 5.9255. Min Act: -0.1700
Data Index: 5668233 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1443. Min Range: -6.1443
Max Act: 5.9255. Min Act: -0.1700
Data Index: 1832254 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1443. Min Range: -6.1443
Max Act: 5.9255. Min Act: -0.1700
Data Index: 1256899 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1443. Min Range: -6.1443
Max Act: 5.8943. Min Act: -0.1700
Data Index: 5895557 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1443. Min Range: -6.1443
Max Act: 5.8943. Min Act: -0.1700
Data Index: 3385898 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1443. Min Range: -6.1443
Max Act: 5.8630. Min Act: -0.1700
Data Index: 1255839 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19