Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5841 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.2379. Min Act: -0.1700
Data Index: 5449834 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0504. Min Act: -0.1700
Data Index: 7046144 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0504. Min Act: -0.1700
Data Index: 2577449 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0191. Min Act: -0.1700
Data Index: 3636978 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0816. Min Act: -0.1700
Data Index: 8574540 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0191. Min Act: -0.1700
Data Index: 3786490 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0191. Min Act: -0.1700
Data Index: 567075 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.9879. Min Act: -0.1700
Data Index: 4166488 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.9879. Min Act: -0.1700
Data Index: 8161691 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.9879. Min Act: -0.1700
Data Index: 8193396 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.9879. Min Act: -0.1700
Data Index: 7485628 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.9566. Min Act: -0.1700
Data Index: 8482719 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.9879. Min Act: -0.1700
Data Index: 629935 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.9254. Min Act: -0.1700
Data Index: 6503256 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.9254. Min Act: -0.1700
Data Index: 2709043 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.9254. Min Act: -0.1700
Data Index: 4097614 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.8941. Min Act: -0.1700
Data Index: 1961671 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.9254. Min Act: -0.1700
Data Index: 389104 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.8316. Min Act: -0.1700
Data Index: 8292315 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.8629. Min Act: -0.1700
Data Index: 1958742 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19