Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 119 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3219. Min Range: -4.3219
Max Act: 4.3219. Min Act: -0.1700
Data Index: 5565664 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3219. Min Range: -4.3219
Max Act: 4.3219. Min Act: -0.1700
Data Index: 6791013 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3219. Min Range: -4.3219
Max Act: 4.2594. Min Act: -0.1700
Data Index: 8305065 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3219. Min Range: -4.3219
Max Act: 4.1656. Min Act: -0.1700
Data Index: 3882400 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3219. Min Range: -4.3219
Max Act: 4.1344. Min Act: -0.1700
Data Index: 2429968 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3219. Min Range: -4.3219
Max Act: 4.1344. Min Act: -0.1700
Data Index: 2771990 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3219. Min Range: -4.3219
Max Act: 4.0093. Min Act: -0.1700
Data Index: 728331 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3219. Min Range: -4.3219
Max Act: 4.0093. Min Act: -0.1700
Data Index: 5243782 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3219. Min Range: -4.3219
Max Act: 4.0093. Min Act: -0.1700
Data Index: 4092946 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3219. Min Range: -4.3219
Max Act: 3.9781. Min Act: -0.1700
Data Index: 8697905 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3219. Min Range: -4.3219
Max Act: 3.9468. Min Act: -0.1700
Data Index: 1038827 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3219. Min Range: -4.3219
Max Act: 3.9468. Min Act: -0.1700
Data Index: 3704038 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3219. Min Range: -4.3219
Max Act: 3.9468. Min Act: -0.1700
Data Index: 641868 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3219. Min Range: -4.3219
Max Act: 3.9156. Min Act: -0.1700
Data Index: 2328531 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3219. Min Range: -4.3219
Max Act: 3.9156. Min Act: -0.1700
Data Index: 1369940 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3219. Min Range: -4.3219
Max Act: 3.8843. Min Act: -0.1700
Data Index: 1095084 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3219. Min Range: -4.3219
Max Act: 3.8687. Min Act: -0.1700
Data Index: 1422028 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3219. Min Range: -4.3219
Max Act: 3.8687. Min Act: -0.1700
Data Index: 1389014 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3219. Min Range: -4.3219
Max Act: 3.8530. Min Act: -0.1700
Data Index: 4368639 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3219. Min Range: -4.3219
Max Act: 3.8530. Min Act: -0.1700
Data Index: 4034774 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19