Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 454 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5670. Min Range: -7.5670
Max Act: 7.5670. Min Act: -0.1700
Data Index: 82046 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5670. Min Range: -7.5670
Max Act: 7.3170. Min Act: -0.1700
Data Index: 2594799 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5670. Min Range: -7.5670
Max Act: 7.2857. Min Act: -0.1700
Data Index: 2082036 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5670. Min Range: -7.5670
Max Act: 7.1920. Min Act: -0.1700
Data Index: 4877845 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5670. Min Range: -7.5670
Max Act: 7.0670. Min Act: -0.1700
Data Index: 6147170 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5670. Min Range: -7.5670
Max Act: 7.0982. Min Act: -0.1700
Data Index: 4879453 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5670. Min Range: -7.5670
Max Act: 7.0670. Min Act: -0.1700
Data Index: 4704861 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5670. Min Range: -7.5670
Max Act: 7.0670. Min Act: -0.1700
Data Index: 3359981 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5670. Min Range: -7.5670
Max Act: 7.0670. Min Act: -0.1700
Data Index: 8267990 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5670. Min Range: -7.5670
Max Act: 7.0045. Min Act: -0.1700
Data Index: 7519376 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5670. Min Range: -7.5670
Max Act: 6.9732. Min Act: -0.1700
Data Index: 5422168 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5670. Min Range: -7.5670
Max Act: 6.9732. Min Act: -0.1700
Data Index: 65447 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5670. Min Range: -7.5670
Max Act: 6.9732. Min Act: -0.1700
Data Index: 286227 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5670. Min Range: -7.5670
Max Act: 6.9420. Min Act: -0.1700
Data Index: 4349238 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5670. Min Range: -7.5670
Max Act: 6.9420. Min Act: -0.1700
Data Index: 5988306 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5670. Min Range: -7.5670
Max Act: 6.9107. Min Act: -0.1700
Data Index: 1971038 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5670. Min Range: -7.5670
Max Act: 6.8482. Min Act: -0.1700
Data Index: 5079671 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5670. Min Range: -7.5670
Max Act: 6.8795. Min Act: -0.1700
Data Index: 6189614 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5670. Min Range: -7.5670
Max Act: 6.9107. Min Act: -0.1700
Data Index: 4041395 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5670. Min Range: -7.5670
Max Act: 6.8795. Min Act: -0.1700
Data Index: 4461780 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19