Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2727 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.9790. Min Act: -0.1700
Data Index: 6908784 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.9477. Min Act: -0.1700
Data Index: 5079361 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.9165. Min Act: -0.1700
Data Index: 7176590 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.9165. Min Act: -0.1700
Data Index: 8233345 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.8852. Min Act: -0.1700
Data Index: 3879369 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.8852. Min Act: -0.1700
Data Index: 3629555 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.7602. Min Act: -0.1700
Data Index: 6226729 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.7602. Min Act: -0.1700
Data Index: 1954725 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.7290. Min Act: -0.1700
Data Index: 754005 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.7290. Min Act: -0.1700
Data Index: 5829493 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.6665. Min Act: -0.1700
Data Index: 4499324 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.7290. Min Act: -0.1700
Data Index: 545352 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.6352. Min Act: -0.1700
Data Index: 7345216 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.6665. Min Act: -0.1700
Data Index: 881942 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.6665. Min Act: -0.1700
Data Index: 8233339 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.6665. Min Act: -0.1700
Data Index: 3124725 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.6352. Min Act: -0.1700
Data Index: 7205455 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.6352. Min Act: -0.1700
Data Index: 7997914 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.6352. Min Act: -0.1700
Data Index: 5673222 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9790. Min Range: -5.9790
Max Act: 5.6040. Min Act: -0.1700
Data Index: 2038900 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19