Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2068 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.7475. Min Act: -0.1700
Data Index: 4479647 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.6225. Min Act: -0.1700
Data Index: 5537059 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.6225. Min Act: -0.1700
Data Index: 1510361 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.6225. Min Act: -0.1700
Data Index: 7578051 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.5913. Min Act: -0.1700
Data Index: 4423270 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.5913. Min Act: -0.1700
Data Index: 3466819 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.5600. Min Act: -0.1700
Data Index: 3244765 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4975. Min Act: -0.1700
Data Index: 4255398 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.5288. Min Act: -0.1700
Data Index: 8375456 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4663. Min Act: -0.1700
Data Index: 4639222 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4663. Min Act: -0.1700
Data Index: 6297948 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.3413. Min Act: -0.1700
Data Index: 8782923 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.3100. Min Act: -0.1700
Data Index: 8475982 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.2788. Min Act: -0.1700
Data Index: 3247439 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.2788. Min Act: -0.1700
Data Index: 7420536 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.2788. Min Act: -0.1700
Data Index: 1986366 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.2475. Min Act: -0.1700
Data Index: 5035706 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.2475. Min Act: -0.1700
Data Index: 1640313 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.2475. Min Act: -0.1700
Data Index: 2721486 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.2163. Min Act: -0.1700
Data Index: 4544836 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19