Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 727 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0539. Min Range: -5.0539
Max Act: 5.0539. Min Act: -0.1700
Data Index: 7669121 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.9289. Min Act: -0.1700
Data Index: 2806642 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.9289. Min Act: -0.1700
Data Index: 1060482 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.9289. Min Act: -0.1700
Data Index: 8780656 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.9289. Min Act: -0.1700
Data Index: 8566238 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.8976. Min Act: -0.1700
Data Index: 861748 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.9289. Min Act: -0.1700
Data Index: 4834881 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.8664. Min Act: -0.1700
Data Index: 3139854 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.8351. Min Act: -0.1700
Data Index: 5095381 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.8351. Min Act: -0.1700
Data Index: 1235223 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.8039. Min Act: -0.1700
Data Index: 7283056 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.8351. Min Act: -0.1700
Data Index: 3590377 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.8351. Min Act: -0.1700
Data Index: 8158148 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.8039. Min Act: -0.1700
Data Index: 7249543 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.8039. Min Act: -0.1700
Data Index: 8636409 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.8039. Min Act: -0.1700
Data Index: 1062501 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.7726. Min Act: -0.1700
Data Index: 5531439 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.7726. Min Act: -0.1700
Data Index: 5838799 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.7726. Min Act: -0.1700
Data Index: 623036 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0539. Min Range: -5.0539
Max Act: 4.7414. Min Act: -0.1700
Data Index: 985827 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19