Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3539 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.8226. Min Act: -0.1700
Data Index: 3571079 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.6975. Min Act: -0.1700
Data Index: 1388486 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.6193. Min Act: -0.1700
Data Index: 5910912 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.5723. Min Act: -0.1700
Data Index: 4035871 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.5880. Min Act: -0.1700
Data Index: 6406748 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.5097. Min Act: -0.1700
Data Index: 6646026 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.4784. Min Act: -0.1700
Data Index: 6829152 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.4627. Min Act: -0.1700
Data Index: 1532891 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.4627. Min Act: -0.1700
Data Index: 410213 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.4314. Min Act: -0.1700
Data Index: 7300217 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.4314. Min Act: -0.1700
Data Index: 701665 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.4000. Min Act: -0.1700
Data Index: 5959471 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.4000. Min Act: -0.1700
Data Index: 4883704 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.4000. Min Act: -0.1700
Data Index: 3110495 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.3687. Min Act: -0.1700
Data Index: 8152301 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.3687. Min Act: -0.1700
Data Index: 1137707 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.3687. Min Act: -0.1700
Data Index: 7804809 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.3687. Min Act: -0.1700
Data Index: 5469914 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.3687. Min Act: -0.1700
Data Index: 6335603 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8226. Min Range: -3.8226
Max Act: 3.3687. Min Act: -0.1700
Data Index: 1767375 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19