Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 41 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.4504. Min Act: -0.1700
Data Index: 2618054 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.3567. Min Act: -0.1700
Data Index: 5971160 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.2942. Min Act: -0.1700
Data Index: 1365707 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.1379. Min Act: -0.1700
Data Index: 5520032 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.1379. Min Act: -0.1700
Data Index: 7893651 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.1067. Min Act: -0.1700
Data Index: 251336 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4504. Min Range: -6.4504
Max Act: 6.0442. Min Act: -0.1700
Data Index: 5960846 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.9817. Min Act: -0.1700
Data Index: 2016247 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.9817. Min Act: -0.1700
Data Index: 5751631 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.8879. Min Act: -0.1700
Data Index: 6073968 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.9192. Min Act: -0.1700
Data Index: 2572226 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.8567. Min Act: -0.1700
Data Index: 2334211 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.8567. Min Act: -0.1700
Data Index: 8250538 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.8567. Min Act: -0.1700
Data Index: 3541954 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.8567. Min Act: -0.1700
Data Index: 1194052 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.8879. Min Act: -0.1700
Data Index: 282989 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.8567. Min Act: -0.1700
Data Index: 6451381 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.7942. Min Act: -0.1700
Data Index: 7341163 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.8254. Min Act: -0.1700
Data Index: 5888411 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4504. Min Range: -6.4504
Max Act: 5.7942. Min Act: -0.1700
Data Index: 971527 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19