Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2027 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.9274. Min Act: -0.1700
Data Index: 4608235 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.6774. Min Act: -0.1700
Data Index: 2179112 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.5524. Min Act: -0.1700
Data Index: 7673741 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.5836. Min Act: -0.1700
Data Index: 793411 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.4899. Min Act: -0.1700
Data Index: 6874730 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.4899. Min Act: -0.1700
Data Index: 7127207 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.4586. Min Act: -0.1700
Data Index: 5407471 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.4274. Min Act: -0.1700
Data Index: 5405591 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.4274. Min Act: -0.1700
Data Index: 6130808 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.3336. Min Act: -0.1700
Data Index: 2988660 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.3649. Min Act: -0.1700
Data Index: 7498746 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.3024. Min Act: -0.1700
Data Index: 3360037 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.3024. Min Act: -0.1700
Data Index: 8432834 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.2711. Min Act: -0.1700
Data Index: 1132484 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.2399. Min Act: -0.1700
Data Index: 5675422 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.2399. Min Act: -0.1700
Data Index: 8095372 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.2399. Min Act: -0.1700
Data Index: 388038 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.2399. Min Act: -0.1700
Data Index: 6495133 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.2086. Min Act: -0.1700
Data Index: 8484584 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9274. Min Range: -7.9274
Max Act: 7.1774. Min Act: -0.1700
Data Index: 7829250 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19