Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.9001. Min Act: -0.1700
Data Index: 7959043 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.8688. Min Act: -0.1700
Data Index: 8601108 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.8376. Min Act: -0.1700
Data Index: 3002549 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.8219. Min Act: -0.1700
Data Index: 6402046 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.7907. Min Act: -0.1700
Data Index: 4230869 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.7750. Min Act: -0.1700
Data Index: 343602 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.7594. Min Act: -0.1700
Data Index: 1886414 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.7438. Min Act: -0.1700
Data Index: 3750435 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.7281. Min Act: -0.1700
Data Index: 2826343 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.6968. Min Act: -0.1700
Data Index: 2016139 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.6968. Min Act: -0.1700
Data Index: 3933844 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.7125. Min Act: -0.1700
Data Index: 4193384 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.6812. Min Act: -0.1700
Data Index: 538751 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.6812. Min Act: -0.1700
Data Index: 5643186 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.6812. Min Act: -0.1700
Data Index: 3774236 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.6655. Min Act: -0.1700
Data Index: 7531199 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.6655. Min Act: -0.1700
Data Index: 7541044 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.6655. Min Act: -0.1700
Data Index: 5673086 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.6499. Min Act: -0.1700
Data Index: 5818478 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9001. Min Range: -3.9001
Max Act: 3.6499. Min Act: -0.1700
Data Index: 2440288 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19