Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 532 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0192. Min Range: -5.0192
Max Act: 5.0192. Min Act: -0.1700
Data Index: 6837157 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0192. Min Range: -5.0192
Max Act: 5.0192. Min Act: -0.1700
Data Index: 6837152 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.9880. Min Act: -0.1700
Data Index: 483566 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.9880. Min Act: -0.1700
Data Index: 1493166 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.9255. Min Act: -0.1700
Data Index: 3809207 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.9255. Min Act: -0.1700
Data Index: 4811069 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.9255. Min Act: -0.1700
Data Index: 3953568 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.9255. Min Act: -0.1700
Data Index: 4525544 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.8630. Min Act: -0.1700
Data Index: 483565 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.8630. Min Act: -0.1700
Data Index: 2116402 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.8317. Min Act: -0.1700
Data Index: 6860323 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.8317. Min Act: -0.1700
Data Index: 3518780 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.8317. Min Act: -0.1700
Data Index: 4525545 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.8005. Min Act: -0.1700
Data Index: 609361 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.8005. Min Act: -0.1700
Data Index: 1493168 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.7380. Min Act: -0.1700
Data Index: 4605256 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.7692. Min Act: -0.1700
Data Index: 8040899 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.7380. Min Act: -0.1700
Data Index: 7446686 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.7067. Min Act: -0.1700
Data Index: 483567 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0192. Min Range: -5.0192
Max Act: 4.7067. Min Act: -0.1700
Data Index: 8040898 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19