Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5729 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1325. Min Range: -5.1325
Max Act: 5.1325. Min Act: -0.1700
Data Index: 1111523 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1325. Min Range: -5.1325
Max Act: 5.1325. Min Act: -0.1700
Data Index: 6228560 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1325. Min Range: -5.1325
Max Act: 5.0387. Min Act: -0.1700
Data Index: 1575055 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1325. Min Range: -5.1325
Max Act: 5.0700. Min Act: -0.1700
Data Index: 311227 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1325. Min Range: -5.1325
Max Act: 5.0700. Min Act: -0.1700
Data Index: 3143394 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1325. Min Range: -5.1325
Max Act: 5.0700. Min Act: -0.1700
Data Index: 1784497 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1325. Min Range: -5.1325
Max Act: 5.0387. Min Act: -0.1700
Data Index: 4637501 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1325. Min Range: -5.1325
Max Act: 5.0075. Min Act: -0.1700
Data Index: 881606 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1325. Min Range: -5.1325
Max Act: 5.0075. Min Act: -0.1700
Data Index: 1784496 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1325. Min Range: -5.1325
Max Act: 5.0075. Min Act: -0.1700
Data Index: 5191382 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1325. Min Range: -5.1325
Max Act: 4.9762. Min Act: -0.1700
Data Index: 3028783 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1325. Min Range: -5.1325
Max Act: 4.9450. Min Act: -0.1700
Data Index: 4068973 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1325. Min Range: -5.1325
Max Act: 4.9137. Min Act: -0.1700
Data Index: 5080346 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1325. Min Range: -5.1325
Max Act: 4.9762. Min Act: -0.1700
Data Index: 4719125 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1325. Min Range: -5.1325
Max Act: 4.9450. Min Act: -0.1700
Data Index: 7543538 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1325. Min Range: -5.1325
Max Act: 4.9450. Min Act: -0.1700
Data Index: 4846639 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1325. Min Range: -5.1325
Max Act: 4.9450. Min Act: -0.1700
Data Index: 6064775 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1325. Min Range: -5.1325
Max Act: 4.9137. Min Act: -0.1700
Data Index: 5511243 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1325. Min Range: -5.1325
Max Act: 4.9137. Min Act: -0.1700
Data Index: 5997349 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1325. Min Range: -5.1325
Max Act: 4.9450. Min Act: -0.1700
Data Index: 5482196 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19