Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4101 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.7868. Min Act: -0.1700
Data Index: 6669429 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.7243. Min Act: -0.1700
Data Index: 689721 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.6618. Min Act: -0.1700
Data Index: 689719 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.5993. Min Act: -0.1700
Data Index: 4617854 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.5368. Min Act: -0.1700
Data Index: 689720 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.4743. Min Act: -0.1700
Data Index: 689704 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.4743. Min Act: -0.1700
Data Index: 689706 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.3493. Min Act: -0.1700
Data Index: 6835170 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.4118. Min Act: -0.1700
Data Index: 4454506 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.2868. Min Act: -0.1700
Data Index: 4746674 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.3493. Min Act: -0.1700
Data Index: 8505351 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.2868. Min Act: -0.1699
Data Index: 7905351 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.2243. Min Act: -0.1700
Data Index: 1234222 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.2868. Min Act: -0.1700
Data Index: 5427597 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.2243. Min Act: -0.1700
Data Index: 7811280 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.2868. Min Act: -0.1700
Data Index: 5124421 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.1618. Min Act: -0.1700
Data Index: 1848851 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.1618. Min Act: -0.1700
Data Index: 1257138 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.1618. Min Act: -0.1700
Data Index: 1771279 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7868. Min Range: -9.7868
Max Act: 9.2243. Min Act: -0.1700
Data Index: 8396155 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19