Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 460 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.6433. Min Act: -0.1700
Data Index: 5379696 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.6121. Min Act: -0.1700
Data Index: 886257 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.6121. Min Act: -0.1700
Data Index: 8569354 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.6121. Min Act: -0.1700
Data Index: 7199799 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.6121. Min Act: -0.1700
Data Index: 3817398 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.6433. Min Act: -0.1700
Data Index: 4191134 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.6121. Min Act: -0.1700
Data Index: 356324 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.5808. Min Act: -0.1700
Data Index: 7141845 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.5808. Min Act: -0.1700
Data Index: 1237594 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.5808. Min Act: -0.1700
Data Index: 5480223 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.5808. Min Act: -0.1700
Data Index: 8514109 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.5496. Min Act: -0.1700
Data Index: 604735 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.5183. Min Act: -0.1700
Data Index: 7171482 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.5496. Min Act: -0.1700
Data Index: 180487 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.5183. Min Act: -0.1700
Data Index: 6364649 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.5496. Min Act: -0.1700
Data Index: 8403248 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.5183. Min Act: -0.1700
Data Index: 6941560 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.5183. Min Act: -0.1700
Data Index: 2223492 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.5183. Min Act: -0.1700
Data Index: 4355760 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6433. Min Range: -5.6433
Max Act: 5.5183. Min Act: -0.1700
Data Index: 2490889 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19