Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3175 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.3105. Min Act: -0.1700
Data Index: 2170087 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.1855. Min Act: -0.1700
Data Index: 4084199 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.1230. Min Act: -0.1700
Data Index: 4537950 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.1543. Min Act: -0.1700
Data Index: 736730 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.0918. Min Act: -0.1700
Data Index: 1419790 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.1230. Min Act: -0.1700
Data Index: 7549830 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.0918. Min Act: -0.1700
Data Index: 8164506 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.0605. Min Act: -0.1700
Data Index: 1656384 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.0605. Min Act: -0.1700
Data Index: 5734916 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.0605. Min Act: -0.1700
Data Index: 6403408 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.0605. Min Act: -0.1700
Data Index: 8444522 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.0292. Min Act: -0.1700
Data Index: 261850 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.0292. Min Act: -0.1700
Data Index: 1749571 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.0136. Min Act: -0.1700
Data Index: 8357425 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.0292. Min Act: -0.1700
Data Index: 5285641 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.0136. Min Act: -0.1700
Data Index: 2273303 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.0136. Min Act: -0.1700
Data Index: 1768903 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.0292. Min Act: -0.1700
Data Index: 5806854 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3105. Min Range: -4.3105
Max Act: 4.0292. Min Act: -0.1700
Data Index: 6649981 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3105. Min Range: -4.3105
Max Act: 3.9980. Min Act: -0.1700
Data Index: 3096491 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19