Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5739 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.9997. Min Act: -0.1700
Data Index: 4426597 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.7809. Min Act: -0.1700
Data Index: 3591684 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.6872. Min Act: -0.1700
Data Index: 7619324 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.6247. Min Act: -0.1700
Data Index: 354380 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.6247. Min Act: -0.1700
Data Index: 5573517 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.5622. Min Act: -0.1700
Data Index: 8570099 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4997. Min Act: -0.1700
Data Index: 1778286 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4997. Min Act: -0.1700
Data Index: 4084921 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4997. Min Act: -0.1700
Data Index: 3241914 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4684. Min Act: -0.1700
Data Index: 8187719 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4059. Min Act: -0.1700
Data Index: 6051326 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4059. Min Act: -0.1700
Data Index: 6339342 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.3434. Min Act: -0.1700
Data Index: 8532750 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.3122. Min Act: -0.1700
Data Index: 5946370 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.2809. Min Act: -0.1700
Data Index: 4193972 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.2809. Min Act: -0.1700
Data Index: 515039 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.2809. Min Act: -0.1700
Data Index: 29560 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.2497. Min Act: -0.1700
Data Index: 5890206 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.2497. Min Act: -0.1700
Data Index: 8093790 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.2497. Min Act: -0.1700
Data Index: 2004922 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19