Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4343 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3973. Min Range: -9.3973
Max Act: 9.3973. Min Act: -0.1700
Data Index: 6424980 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3973. Min Range: -9.3973
Max Act: 9.3973. Min Act: -0.1700
Data Index: 2131202 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3973. Min Range: -9.3973
Max Act: 9.3348. Min Act: -0.1700
Data Index: 4042687 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3973. Min Range: -9.3973
Max Act: 9.2723. Min Act: -0.1700
Data Index: 5732875 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3973. Min Range: -9.3973
Max Act: 9.2723. Min Act: -0.1700
Data Index: 8731317 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3973. Min Range: -9.3973
Max Act: 9.2098. Min Act: -0.1700
Data Index: 4422630 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3973. Min Range: -9.3973
Max Act: 9.1473. Min Act: -0.1700
Data Index: 7017815 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3973. Min Range: -9.3973
Max Act: 9.0848. Min Act: -0.1700
Data Index: 3467507 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.8973. Min Act: -0.1700
Data Index: 8170442 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.9598. Min Act: -0.1700
Data Index: 301267 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.9598. Min Act: -0.1700
Data Index: 4944119 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.9598. Min Act: -0.1700
Data Index: 3545198 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.9598. Min Act: -0.1700
Data Index: 7768310 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.9598. Min Act: -0.1700
Data Index: 2131204 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.8348. Min Act: -0.1700
Data Index: 4406926 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.8973. Min Act: -0.1700
Data Index: 1033568 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.8348. Min Act: -0.1700
Data Index: 3377904 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.8348. Min Act: -0.1700
Data Index: 72505 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.8348. Min Act: -0.1700
Data Index: 743361 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.8348. Min Act: -0.1700
Data Index: 5403664 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19