Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3760 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.8174. Min Act: -0.1700
Data Index: 1699976 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.5986. Min Act: -0.1700
Data Index: 6846673 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.5674. Min Act: -0.1700
Data Index: 1016543 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.4736. Min Act: -0.1700
Data Index: 2983444 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.3486. Min Act: -0.1700
Data Index: 4200283 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.3174. Min Act: -0.1700
Data Index: 5748740 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.2861. Min Act: -0.1700
Data Index: 7008124 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.2236. Min Act: -0.1700
Data Index: 1010449 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.2236. Min Act: -0.1700
Data Index: 3816698 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.2236. Min Act: -0.1700
Data Index: 3849386 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.2236. Min Act: -0.1700
Data Index: 3641634 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.1924. Min Act: -0.1700
Data Index: 7636320 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.1924. Min Act: -0.1700
Data Index: 3405187 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.1299. Min Act: -0.1700
Data Index: 3926593 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.1299. Min Act: -0.1700
Data Index: 3610677 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.0986. Min Act: -0.1700
Data Index: 2917991 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.0674. Min Act: -0.1700
Data Index: 2672920 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.0674. Min Act: -0.1700
Data Index: 3913131 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.0674. Min Act: -0.1700
Data Index: 5274362 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8174. Min Range: -6.8174
Max Act: 6.0674. Min Act: -0.1700
Data Index: 4015340 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19