Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.3299. Min Act: -0.1700
Data Index: 2775425 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.1736. Min Act: -0.1700
Data Index: 384811 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.1111. Min Act: -0.1700
Data Index: 3191043 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.0799. Min Act: -0.1700
Data Index: 5256488 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.0486. Min Act: -0.1700
Data Index: 2753267 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3299. Min Range: -5.3299
Max Act: 5.0174. Min Act: -0.1700
Data Index: 5112725 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3299. Min Range: -5.3299
Max Act: 4.9549. Min Act: -0.1700
Data Index: 2485850 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3299. Min Range: -5.3299
Max Act: 4.9549. Min Act: -0.1700
Data Index: 5842709 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3299. Min Range: -5.3299
Max Act: 4.9236. Min Act: -0.1700
Data Index: 5627688 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3299. Min Range: -5.3299
Max Act: 4.9236. Min Act: -0.1700
Data Index: 3847894 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3299. Min Range: -5.3299
Max Act: 4.9236. Min Act: -0.1700
Data Index: 6558768 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3299. Min Range: -5.3299
Max Act: 4.9236. Min Act: -0.1700
Data Index: 1282800 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3299. Min Range: -5.3299
Max Act: 4.9236. Min Act: -0.1700
Data Index: 6171817 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3299. Min Range: -5.3299
Max Act: 4.8611. Min Act: -0.1700
Data Index: 2619278 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3299. Min Range: -5.3299
Max Act: 4.8611. Min Act: -0.1700
Data Index: 6769952 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3299. Min Range: -5.3299
Max Act: 4.8611. Min Act: -0.1700
Data Index: 2261144 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3299. Min Range: -5.3299
Max Act: 4.8611. Min Act: -0.1700
Data Index: 5704732 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3299. Min Range: -5.3299
Max Act: 4.8299. Min Act: -0.1700
Data Index: 1142496 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3299. Min Range: -5.3299
Max Act: 4.8299. Min Act: -0.1700
Data Index: 3279074 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3299. Min Range: -5.3299
Max Act: 4.8299. Min Act: -0.1700
Data Index: 3650225 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19