Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 762 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6007. Min Range: -7.6007
Max Act: 7.6007. Min Act: -0.1700
Data Index: 818642 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.9132. Min Act: -0.1700
Data Index: 4628731 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.6632. Min Act: -0.1700
Data Index: 4628732 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.6632. Min Act: -0.1700
Data Index: 7053287 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.5695. Min Act: -0.1700
Data Index: 7116448 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.5382. Min Act: -0.1700
Data Index: 7113576 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.4445. Min Act: -0.1700
Data Index: 4582757 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.4132. Min Act: -0.1700
Data Index: 2011384 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.3507. Min Act: -0.1700
Data Index: 5040452 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.3507. Min Act: -0.1700
Data Index: 7015318 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.3507. Min Act: -0.1700
Data Index: 4718885 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.3195. Min Act: -0.1700
Data Index: 5967583 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.3507. Min Act: -0.1700
Data Index: 5922554 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.3195. Min Act: -0.1700
Data Index: 2587269 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.2570. Min Act: -0.1700
Data Index: 7818215 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.1632. Min Act: -0.1700
Data Index: 8297873 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.1320. Min Act: -0.1700
Data Index: 298472 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.1007. Min Act: -0.1700
Data Index: 5854940 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.1320. Min Act: -0.1700
Data Index: 7799067 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6007. Min Range: -7.6007
Max Act: 6.1007. Min Act: -0.1700
Data Index: 1106197 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19