Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2585 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1165. Min Range: -6.1165
Max Act: 6.1165. Min Act: -0.1700
Data Index: 406520 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.8978. Min Act: -0.1700
Data Index: 7976842 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.8040. Min Act: -0.1700
Data Index: 3030380 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.6790. Min Act: -0.1700
Data Index: 8754574 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.6790. Min Act: -0.1700
Data Index: 5674031 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.6790. Min Act: -0.1700
Data Index: 451911 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.6790. Min Act: -0.1700
Data Index: 2412751 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.6478. Min Act: -0.1700
Data Index: 3232954 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.6478. Min Act: -0.1700
Data Index: 5872399 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.6165. Min Act: -0.1700
Data Index: 5069997 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.6165. Min Act: -0.1700
Data Index: 6468517 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.6165. Min Act: -0.1700
Data Index: 6520496 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.5853. Min Act: -0.1700
Data Index: 5988565 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.6165. Min Act: -0.1700
Data Index: 1426295 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.5853. Min Act: -0.1700
Data Index: 5318620 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.5853. Min Act: -0.1700
Data Index: 6109136 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.5540. Min Act: -0.1700
Data Index: 2676971 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.5228. Min Act: -0.1700
Data Index: 5609036 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.5540. Min Act: -0.1700
Data Index: 6300633 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1165. Min Range: -6.1165
Max Act: 5.5540. Min Act: -0.1700
Data Index: 5697106 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19