Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3233 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.3918. Min Act: -0.1700
Data Index: 5686921 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.2356. Min Act: -0.1700
Data Index: 3811067 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.2043. Min Act: -0.1700
Data Index: 5202154 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.1730. Min Act: -0.1700
Data Index: 4037804 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.1418. Min Act: -0.1700
Data Index: 5159460 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.1730. Min Act: -0.1700
Data Index: 869164 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.1730. Min Act: -0.1700
Data Index: 1615283 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.1418. Min Act: -0.1700
Data Index: 914346 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.1418. Min Act: -0.1700
Data Index: 7969208 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.0793. Min Act: -0.1700
Data Index: 7909023 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.0480. Min Act: -0.1700
Data Index: 4737288 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.0480. Min Act: -0.1700
Data Index: 8239970 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.0480. Min Act: -0.1700
Data Index: 858991 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.0793. Min Act: -0.1700
Data Index: 340351 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.0168. Min Act: -0.1700
Data Index: 2400627 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.0168. Min Act: -0.1700
Data Index: 1513495 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3918. Min Range: -4.3918
Max Act: 3.9855. Min Act: -0.1700
Data Index: 2288493 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3918. Min Range: -4.3918
Max Act: 4.0168. Min Act: -0.1700
Data Index: 6587214 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3918. Min Range: -4.3918
Max Act: 3.9855. Min Act: -0.1700
Data Index: 384930 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3918. Min Range: -4.3918
Max Act: 3.9855. Min Act: -0.1700
Data Index: 7306214 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19