Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2664 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.6224. Min Act: -0.1700
Data Index: 959398 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.5741. Min Act: -0.1700
Data Index: 2685723 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.5580. Min Act: -0.1700
Data Index: 4282960 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.5256. Min Act: -0.1700
Data Index: 1376148 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.4933. Min Act: -0.1700
Data Index: 959021 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.5095. Min Act: -0.1700
Data Index: 780529 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.4770. Min Act: -0.1700
Data Index: 3454945 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.4770. Min Act: -0.1700
Data Index: 1287638 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.4933. Min Act: -0.1700
Data Index: 7954048 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.4446. Min Act: -0.1700
Data Index: 780524 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.4446. Min Act: -0.1700
Data Index: 4956525 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.4446. Min Act: -0.1700
Data Index: 4553356 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.3957. Min Act: -0.1700
Data Index: 2784973 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.4120. Min Act: -0.1700
Data Index: 4400433 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.4120. Min Act: -0.1700
Data Index: 885261 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.3957. Min Act: -0.1700
Data Index: 1813085 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.3957. Min Act: -0.1700
Data Index: 8241903 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.3957. Min Act: -0.1700
Data Index: 6509779 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.3957. Min Act: -0.1700
Data Index: 5527288 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6224. Min Range: -2.6224
Max Act: 2.3630. Min Act: -0.1700
Data Index: 3578007 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19