Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 356 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.2346. Min Act: -0.1700
Data Index: 775670 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.2346. Min Act: -0.1700
Data Index: 570492 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.2346. Min Act: -0.1700
Data Index: 2065078 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.2346. Min Act: -0.1700
Data Index: 1708804 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.2346. Min Act: -0.1700
Data Index: 1730386 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.2033. Min Act: -0.1700
Data Index: 5655210 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.2033. Min Act: -0.1700
Data Index: 8128707 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.1721. Min Act: -0.1700
Data Index: 7379413 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.2346. Min Act: -0.1700
Data Index: 6320993 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.2033. Min Act: -0.1700
Data Index: 2385946 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.2033. Min Act: -0.1700
Data Index: 4890919 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.2033. Min Act: -0.1700
Data Index: 1862635 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.1721. Min Act: -0.1700
Data Index: 1591695 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.1721. Min Act: -0.1700
Data Index: 1708799 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.1721. Min Act: -0.1700
Data Index: 1708800 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.1721. Min Act: -0.1700
Data Index: 4367663 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.1721. Min Act: -0.1700
Data Index: 1955313 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.1721. Min Act: -0.1700
Data Index: 2503957 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.1721. Min Act: -0.1700
Data Index: 3362459 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2346. Min Range: -4.2346
Max Act: 4.1721. Min Act: -0.1700
Data Index: 7841924 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19