Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3664. Min Range: -6.3664
Max Act: 6.3664. Min Act: -0.1700
Data Index: 8639001 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3664. Min Range: -6.3664
Max Act: 6.3664. Min Act: -0.1700
Data Index: 6064015 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3664. Min Range: -6.3664
Max Act: 6.1164. Min Act: -0.1700
Data Index: 865586 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3664. Min Range: -6.3664
Max Act: 6.0539. Min Act: -0.1700
Data Index: 3830414 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3664. Min Range: -6.3664
Max Act: 6.0227. Min Act: -0.1700
Data Index: 1757721 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3664. Min Range: -6.3664
Max Act: 5.9289. Min Act: -0.1700
Data Index: 3632143 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3664. Min Range: -6.3664
Max Act: 5.9289. Min Act: -0.1700
Data Index: 702843 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3664. Min Range: -6.3664
Max Act: 5.9289. Min Act: -0.1700
Data Index: 8709036 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3664. Min Range: -6.3664
Max Act: 5.8977. Min Act: -0.1700
Data Index: 7080740 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3664. Min Range: -6.3664
Max Act: 5.8977. Min Act: -0.1700
Data Index: 2036622 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3664. Min Range: -6.3664
Max Act: 5.8352. Min Act: -0.1700
Data Index: 357533 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3664. Min Range: -6.3664
Max Act: 5.8352. Min Act: -0.1700
Data Index: 3898108 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3664. Min Range: -6.3664
Max Act: 5.8039. Min Act: -0.1700
Data Index: 2003281 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3664. Min Range: -6.3664
Max Act: 5.8352. Min Act: -0.1700
Data Index: 526327 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3664. Min Range: -6.3664
Max Act: 5.8039. Min Act: -0.1700
Data Index: 1932668 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3664. Min Range: -6.3664
Max Act: 5.8039. Min Act: -0.1700
Data Index: 5213061 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3664. Min Range: -6.3664
Max Act: 5.7414. Min Act: -0.1700
Data Index: 6664236 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3664. Min Range: -6.3664
Max Act: 5.7727. Min Act: -0.1700
Data Index: 6152425 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3664. Min Range: -6.3664
Max Act: 5.7414. Min Act: -0.1700
Data Index: 8709038 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3664. Min Range: -6.3664
Max Act: 5.7727. Min Act: -0.1700
Data Index: 5492673 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19