Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4358 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1649. Min Range: -6.1649
Max Act: 6.1649. Min Act: -0.1700
Data Index: 5064988 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.9462. Min Act: -0.1700
Data Index: 4902570 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.8212. Min Act: -0.1700
Data Index: 2657289 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.7587. Min Act: -0.1700
Data Index: 3460502 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.6962. Min Act: -0.1700
Data Index: 5595359 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.6962. Min Act: -0.1700
Data Index: 5380088 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.6962. Min Act: -0.1700
Data Index: 1180220 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.6024. Min Act: -0.1700
Data Index: 2299429 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.5712. Min Act: -0.1700
Data Index: 5792434 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.5399. Min Act: -0.1700
Data Index: 3977928 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.5399. Min Act: -0.1700
Data Index: 6133370 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.6024. Min Act: -0.1700
Data Index: 2350779 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.6024. Min Act: -0.1700
Data Index: 3491947 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.5712. Min Act: -0.1700
Data Index: 3446543 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.5087. Min Act: -0.1700
Data Index: 6954857 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.5087. Min Act: -0.1700
Data Index: 7061627 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.5087. Min Act: -0.1700
Data Index: 2210439 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.4774. Min Act: -0.1700
Data Index: 6191189 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.4774. Min Act: -0.1700
Data Index: 1748142 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1649. Min Range: -6.1649
Max Act: 5.4774. Min Act: -0.1700
Data Index: 5605995 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19