Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2600 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2666. Min Range: -6.2666
Max Act: 6.2666. Min Act: -0.1700
Data Index: 3968754 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2666. Min Range: -6.2666
Max Act: 6.2041. Min Act: -0.1700
Data Index: 5819350 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2666. Min Range: -6.2666
Max Act: 6.0791. Min Act: -0.1700
Data Index: 2586448 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.9853. Min Act: -0.1700
Data Index: 3822313 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.9853. Min Act: -0.1700
Data Index: 8116373 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.9853. Min Act: -0.1700
Data Index: 422501 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.9853. Min Act: -0.1700
Data Index: 4356439 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.9228. Min Act: -0.1700
Data Index: 7184037 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.9228. Min Act: -0.1700
Data Index: 4157595 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.8916. Min Act: -0.1700
Data Index: 3936035 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.8916. Min Act: -0.1700
Data Index: 2792693 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.8603. Min Act: -0.1700
Data Index: 556415 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.8916. Min Act: -0.1700
Data Index: 5109234 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.8603. Min Act: -0.1700
Data Index: 5052802 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.8916. Min Act: -0.1700
Data Index: 2901272 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.8916. Min Act: -0.1700
Data Index: 218654 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.8291. Min Act: -0.1700
Data Index: 204320 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.8291. Min Act: -0.1700
Data Index: 8730901 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.7978. Min Act: -0.1700
Data Index: 3451544 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2666. Min Range: -6.2666
Max Act: 5.7978. Min Act: -0.1700
Data Index: 6384853 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19