Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 758 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.7848. Min Act: -0.1700
Data Index: 6458515 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.5973. Min Act: -0.1700
Data Index: 5978474 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.5348. Min Act: -0.1700
Data Index: 7506466 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.5661. Min Act: -0.1700
Data Index: 3823647 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.4411. Min Act: -0.1700
Data Index: 2795198 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.4723. Min Act: -0.1700
Data Index: 7377319 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.4411. Min Act: -0.1700
Data Index: 8790064 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.4098. Min Act: -0.1700
Data Index: 3610968 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.4411. Min Act: -0.1700
Data Index: 1521636 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.4411. Min Act: -0.1700
Data Index: 1508546 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.4098. Min Act: -0.1700
Data Index: 8683711 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.4098. Min Act: -0.1700
Data Index: 7374537 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.4098. Min Act: -0.1700
Data Index: 4367422 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.3473. Min Act: -0.1700
Data Index: 5706360 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.3473. Min Act: -0.1700
Data Index: 4485576 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.3473. Min Act: -0.1700
Data Index: 2353551 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.2848. Min Act: -0.1700
Data Index: 3869671 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.3161. Min Act: -0.1700
Data Index: 5013117 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.3473. Min Act: -0.1700
Data Index: 319012 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7848. Min Range: -5.7848
Max Act: 5.3161. Min Act: -0.1700
Data Index: 3318028 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19