Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.2738. Min Act: -0.1700
Data Index: 7755605 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.2113. Min Act: -0.1700
Data Index: 5172268 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.2426. Min Act: -0.1700
Data Index: 7315637 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.1801. Min Act: -0.1700
Data Index: 5767209 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.1801. Min Act: -0.1700
Data Index: 1539178 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.1488. Min Act: -0.1700
Data Index: 2445291 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.1175. Min Act: -0.1700
Data Index: 8630009 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.1175. Min Act: -0.1700
Data Index: 8830197 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.1175. Min Act: -0.1700
Data Index: 3313631 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.0863. Min Act: -0.1700
Data Index: 3710314 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.0550. Min Act: -0.1700
Data Index: 1883754 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.1175. Min Act: -0.1700
Data Index: 3245237 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.0863. Min Act: -0.1700
Data Index: 6465802 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.0863. Min Act: -0.1700
Data Index: 8111415 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.0863. Min Act: -0.1700
Data Index: 763122 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.0550. Min Act: -0.1700
Data Index: 1818724 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.0238. Min Act: -0.1700
Data Index: 8778431 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.0238. Min Act: -0.1700
Data Index: 4945654 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.0238. Min Act: -0.1700
Data Index: 7129676 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2738. Min Range: -4.2738
Max Act: 4.0238. Min Act: -0.1700
Data Index: 8166497 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19