Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3400 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.5357. Min Act: -0.1700
Data Index: 3378357 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.4871. Min Act: -0.1700
Data Index: 4260263 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.4547. Min Act: -0.1700
Data Index: 4042278 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.4384. Min Act: -0.1700
Data Index: 2735928 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.4384. Min Act: -0.1700
Data Index: 3378356 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.4221. Min Act: -0.1700
Data Index: 5957506 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.4058. Min Act: -0.1700
Data Index: 1767438 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.4058. Min Act: -0.1700
Data Index: 222064 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.4058. Min Act: -0.1700
Data Index: 387606 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.4058. Min Act: -0.1700
Data Index: 681215 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.3731. Min Act: -0.1700
Data Index: 8091200 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.3895. Min Act: -0.1700
Data Index: 4479743 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.3895. Min Act: -0.1700
Data Index: 4641506 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.3731. Min Act: -0.1700
Data Index: 8305120 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.3731. Min Act: -0.1700
Data Index: 6858267 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.3731. Min Act: -0.1700
Data Index: 5484181 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.3731. Min Act: -0.1700
Data Index: 1721047 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.3568. Min Act: -0.1700
Data Index: 7572062 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.3568. Min Act: -0.1700
Data Index: 5287044 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5357. Min Range: -2.5357
Max Act: 2.3404. Min Act: -0.1700
Data Index: 3641054 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19