Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2466 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5816. Min Range: -9.5816
Max Act: 9.5816. Min Act: -0.1700
Data Index: 6926484 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5816. Min Range: -9.5816
Max Act: 9.5191. Min Act: -0.1700
Data Index: 664482 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5816. Min Range: -9.5816
Max Act: 9.4566. Min Act: -0.1700
Data Index: 1570774 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5816. Min Range: -9.5816
Max Act: 9.3316. Min Act: -0.1700
Data Index: 2058920 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5816. Min Range: -9.5816
Max Act: 9.1441. Min Act: -0.1700
Data Index: 8773674 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5816. Min Range: -9.5816
Max Act: 9.0816. Min Act: -0.1700
Data Index: 8429653 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5816. Min Range: -9.5816
Max Act: 8.9566. Min Act: -0.1700
Data Index: 8125459 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5816. Min Range: -9.5816
Max Act: 8.9566. Min Act: -0.1700
Data Index: 5717413 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5816. Min Range: -9.5816
Max Act: 8.9566. Min Act: -0.1700
Data Index: 8409502 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5816. Min Range: -9.5816
Max Act: 8.9566. Min Act: -0.1700
Data Index: 2148637 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5816. Min Range: -9.5816
Max Act: 8.9566. Min Act: -0.1700
Data Index: 6701156 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5816. Min Range: -9.5816
Max Act: 8.9566. Min Act: -0.1700
Data Index: 5596231 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5816. Min Range: -9.5816
Max Act: 8.8941. Min Act: -0.1700
Data Index: 1656707 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5816. Min Range: -9.5816
Max Act: 8.8941. Min Act: -0.1700
Data Index: 1374733 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5816. Min Range: -9.5816
Max Act: 8.8316. Min Act: -0.1700
Data Index: 2508174 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5816. Min Range: -9.5816
Max Act: 8.8316. Min Act: -0.1700
Data Index: 7005627 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5816. Min Range: -9.5816
Max Act: 8.8316. Min Act: -0.1700
Data Index: 8085295 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5816. Min Range: -9.5816
Max Act: 8.7691. Min Act: -0.1700
Data Index: 3357438 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5816. Min Range: -9.5816
Max Act: 8.7691. Min Act: -0.1700
Data Index: 4000671 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5816. Min Range: -9.5816
Max Act: 8.7691. Min Act: -0.1700
Data Index: 7052572 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19