Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4211. Min Range: -6.4211
Max Act: 6.4211. Min Act: -0.1700
Data Index: 6721188 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4211. Min Range: -6.4211
Max Act: 6.2023. Min Act: -0.1700
Data Index: 6973338 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4211. Min Range: -6.4211
Max Act: 6.1086. Min Act: -0.1700
Data Index: 6182772 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4211. Min Range: -6.4211
Max Act: 6.0461. Min Act: -0.1700
Data Index: 7565985 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4211. Min Range: -6.4211
Max Act: 6.0148. Min Act: -0.1700
Data Index: 2352591 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4211. Min Range: -6.4211
Max Act: 6.0461. Min Act: -0.1700
Data Index: 7344861 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4211. Min Range: -6.4211
Max Act: 6.0148. Min Act: -0.1700
Data Index: 5330287 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4211. Min Range: -6.4211
Max Act: 6.0148. Min Act: -0.1700
Data Index: 3211782 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4211. Min Range: -6.4211
Max Act: 6.0148. Min Act: -0.1700
Data Index: 5756462 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4211. Min Range: -6.4211
Max Act: 5.9836. Min Act: -0.1700
Data Index: 2530111 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4211. Min Range: -6.4211
Max Act: 5.9523. Min Act: -0.1700
Data Index: 2541099 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4211. Min Range: -6.4211
Max Act: 5.9523. Min Act: -0.1700
Data Index: 231137 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4211. Min Range: -6.4211
Max Act: 5.9211. Min Act: -0.1700
Data Index: 7698912 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4211. Min Range: -6.4211
Max Act: 5.9211. Min Act: -0.1700
Data Index: 2011125 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4211. Min Range: -6.4211
Max Act: 5.8898. Min Act: -0.1700
Data Index: 1407292 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4211. Min Range: -6.4211
Max Act: 5.8586. Min Act: -0.1700
Data Index: 760967 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4211. Min Range: -6.4211
Max Act: 5.8898. Min Act: -0.1700
Data Index: 274620 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4211. Min Range: -6.4211
Max Act: 5.8586. Min Act: -0.1700
Data Index: 7628047 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4211. Min Range: -6.4211
Max Act: 5.8586. Min Act: -0.1700
Data Index: 5451928 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4211. Min Range: -6.4211
Max Act: 5.8898. Min Act: -0.1700
Data Index: 6282363 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19