Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2084 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.9486. Min Act: -0.1700
Data Index: 8417942 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.8235. Min Act: -0.1700
Data Index: 1091845 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.8079. Min Act: -0.1700
Data Index: 6617474 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.8079. Min Act: -0.1700
Data Index: 5884699 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.7923. Min Act: -0.1700
Data Index: 1460824 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.7297. Min Act: -0.1700
Data Index: 1363621 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.6671. Min Act: -0.1700
Data Index: 2531797 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.6984. Min Act: -0.1700
Data Index: 2580211 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.6828. Min Act: -0.1700
Data Index: 2808077 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.6671. Min Act: -0.1700
Data Index: 7986248 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.6984. Min Act: -0.1700
Data Index: 4044475 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.6671. Min Act: -0.1700
Data Index: 7005129 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.6515. Min Act: -0.1700
Data Index: 6874193 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.6671. Min Act: -0.1700
Data Index: 6648126 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.6515. Min Act: -0.1700
Data Index: 3176555 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.7297. Min Act: -0.1700
Data Index: 2302091 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.6984. Min Act: -0.1700
Data Index: 3779846 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.6828. Min Act: -0.1700
Data Index: 8703085 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.6358. Min Act: -0.1700
Data Index: 5103459 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9486. Min Range: -3.9486
Max Act: 3.6515. Min Act: -0.1700
Data Index: 5796156 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19