Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1495 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.6671. Min Act: -0.1700
Data Index: 5257325 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.6359. Min Act: -0.1700
Data Index: 7755556 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.6671. Min Act: -0.1700
Data Index: 7043756 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.5734. Min Act: -0.1700
Data Index: 1402281 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.5109. Min Act: -0.1700
Data Index: 5790366 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.5109. Min Act: -0.1700
Data Index: 8819763 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.4796. Min Act: -0.1700
Data Index: 2913944 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.4796. Min Act: -0.1700
Data Index: 3505674 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.4484. Min Act: -0.1700
Data Index: 8323395 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.4484. Min Act: -0.1700
Data Index: 8489654 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.4484. Min Act: -0.1700
Data Index: 1482172 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.4484. Min Act: -0.1700
Data Index: 7597970 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.4171. Min Act: -0.1700
Data Index: 5762301 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.4171. Min Act: -0.1700
Data Index: 7636468 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.4171. Min Act: -0.1700
Data Index: 5134944 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.4171. Min Act: -0.1700
Data Index: 8484800 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.4171. Min Act: -0.1700
Data Index: 347664 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.4171. Min Act: -0.1700
Data Index: 8435284 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.4171. Min Act: -0.1700
Data Index: 5787573 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6671. Min Range: -6.6671
Max Act: 6.4171. Min Act: -0.1698
Data Index: 4905985 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19