Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 905 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.9237. Min Act: -0.1700
Data Index: 6578650 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.9549. Min Act: -0.1700
Data Index: 7327201 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.9549. Min Act: -0.1700
Data Index: 6094511 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.9549. Min Act: -0.1700
Data Index: 7555400 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.8924. Min Act: -0.1700
Data Index: 2934503 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.8611. Min Act: -0.1700
Data Index: 2227818 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.8611. Min Act: -0.1700
Data Index: 6385394 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.8611. Min Act: -0.1700
Data Index: 4868773 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.8611. Min Act: -0.1700
Data Index: 887834 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.8299. Min Act: -0.1700
Data Index: 3532589 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.8299. Min Act: -0.1700
Data Index: 5413700 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.7986. Min Act: -0.1700
Data Index: 4069919 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.7986. Min Act: -0.1700
Data Index: 7246490 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.7986. Min Act: -0.1700
Data Index: 5502794 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.7986. Min Act: -0.1700
Data Index: 1499645 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.7986. Min Act: -0.1700
Data Index: 790855 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.7986. Min Act: -0.1700
Data Index: 2359864 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.7986. Min Act: -0.1700
Data Index: 1196362 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.7673. Min Act: -0.1700
Data Index: 6430615 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9549. Min Range: -3.9549
Max Act: 3.7673. Min Act: -0.1700
Data Index: 50775 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19