Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2547 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4664. Min Range: -7.4664
Max Act: 7.4664. Min Act: -0.1700
Data Index: 7965705 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4664. Min Range: -7.4664
Max Act: 7.3102. Min Act: -0.1700
Data Index: 6907314 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4664. Min Range: -7.4664
Max Act: 7.3102. Min Act: -0.1700
Data Index: 4324147 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4664. Min Range: -7.4664
Max Act: 7.1539. Min Act: -0.1700
Data Index: 8822751 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4664. Min Range: -7.4664
Max Act: 7.1539. Min Act: -0.1700
Data Index: 8649423 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4664. Min Range: -7.4664
Max Act: 7.0914. Min Act: -0.1700
Data Index: 1611366 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4664. Min Range: -7.4664
Max Act: 7.0914. Min Act: -0.1700
Data Index: 1335603 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4664. Min Range: -7.4664
Max Act: 7.0602. Min Act: -0.1700
Data Index: 356647 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4664. Min Range: -7.4664
Max Act: 6.9977. Min Act: -0.1700
Data Index: 3265609 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4664. Min Range: -7.4664
Max Act: 6.9977. Min Act: -0.1700
Data Index: 88569 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4664. Min Range: -7.4664
Max Act: 6.9977. Min Act: -0.1700
Data Index: 1041181 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4664. Min Range: -7.4664
Max Act: 6.9664. Min Act: -0.1700
Data Index: 5509414 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4664. Min Range: -7.4664
Max Act: 6.9664. Min Act: -0.1700
Data Index: 649145 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4664. Min Range: -7.4664
Max Act: 6.9977. Min Act: -0.1700
Data Index: 5972099 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4664. Min Range: -7.4664
Max Act: 6.9977. Min Act: -0.1700
Data Index: 5778749 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4664. Min Range: -7.4664
Max Act: 6.9664. Min Act: -0.1700
Data Index: 4666931 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4664. Min Range: -7.4664
Max Act: 6.9352. Min Act: -0.1700
Data Index: 6407759 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4664. Min Range: -7.4664
Max Act: 6.9352. Min Act: -0.1700
Data Index: 834860 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4664. Min Range: -7.4664
Max Act: 6.9664. Min Act: -0.1700
Data Index: 2925566 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4664. Min Range: -7.4664
Max Act: 6.9664. Min Act: -0.1700
Data Index: 5695880 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19