Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3511 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.7671. Min Act: -0.1700
Data Index: 340871 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.7046. Min Act: -0.1700
Data Index: 6377900 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.6421. Min Act: -0.1700
Data Index: 3572522 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.6421. Min Act: -0.1700
Data Index: 4092262 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.5796. Min Act: -0.1700
Data Index: 3605061 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.4858. Min Act: -0.1700
Data Index: 5308904 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.5171. Min Act: -0.1700
Data Index: 8581941 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.4858. Min Act: -0.1700
Data Index: 7320396 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.3296. Min Act: -0.1700
Data Index: 567545 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.3296. Min Act: -0.1700
Data Index: 5323069 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.3608. Min Act: -0.1700
Data Index: 2009159 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.3296. Min Act: -0.1700
Data Index: 4561182 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.3296. Min Act: -0.1700
Data Index: 7567649 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.2983. Min Act: -0.1700
Data Index: 6216098 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.2671. Min Act: -0.1700
Data Index: 2266599 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.2671. Min Act: -0.1700
Data Index: 942240 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.2671. Min Act: -0.1700
Data Index: 8690162 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.2358. Min Act: -0.1700
Data Index: 4649224 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.2358. Min Act: -0.1700
Data Index: 6325036 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7671. Min Range: -7.7671
Max Act: 7.2358. Min Act: -0.1700
Data Index: 360452 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19