Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 42 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2679. Min Range: -7.2679
Max Act: 7.2679. Min Act: -0.1700
Data Index: 5176703 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2679. Min Range: -7.2679
Max Act: 7.0804. Min Act: -0.1700
Data Index: 163785 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.8929. Min Act: -0.1700
Data Index: 6360148 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.8617. Min Act: -0.1700
Data Index: 133206 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.8304. Min Act: -0.1700
Data Index: 466612 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.7992. Min Act: -0.1700
Data Index: 6378213 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.7992. Min Act: -0.1700
Data Index: 4571785 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.7992. Min Act: -0.1700
Data Index: 3272174 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.7679. Min Act: -0.1700
Data Index: 4052480 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.7992. Min Act: -0.1700
Data Index: 7814345 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.7367. Min Act: -0.1700
Data Index: 2354514 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.7367. Min Act: -0.1700
Data Index: 4332301 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.7054. Min Act: -0.1700
Data Index: 6519482 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.6742. Min Act: -0.1700
Data Index: 27156 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.6429. Min Act: -0.1700
Data Index: 1671515 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.6117. Min Act: -0.1700
Data Index: 6397718 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.6117. Min Act: -0.1700
Data Index: 2882137 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.6117. Min Act: -0.1700
Data Index: 1782124 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.5804. Min Act: -0.1700
Data Index: 4926482 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2679. Min Range: -7.2679
Max Act: 6.5804. Min Act: -0.1700
Data Index: 7180452 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19