Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3764 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5397. Min Range: -7.5397
Max Act: 7.5397. Min Act: -0.1700
Data Index: 2806565 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5397. Min Range: -7.5397
Max Act: 7.1959. Min Act: -0.1700
Data Index: 2479267 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5397. Min Range: -7.5397
Max Act: 7.1334. Min Act: -0.1700
Data Index: 728899 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5397. Min Range: -7.5397
Max Act: 7.0709. Min Act: -0.1700
Data Index: 1849068 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5397. Min Range: -7.5397
Max Act: 7.0397. Min Act: -0.1700
Data Index: 7713347 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5397. Min Range: -7.5397
Max Act: 7.0084. Min Act: -0.1700
Data Index: 1318137 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5397. Min Range: -7.5397
Max Act: 6.9772. Min Act: -0.1700
Data Index: 4382903 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5397. Min Range: -7.5397
Max Act: 6.9772. Min Act: -0.1700
Data Index: 8355024 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5397. Min Range: -7.5397
Max Act: 6.9147. Min Act: -0.1700
Data Index: 7630213 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5397. Min Range: -7.5397
Max Act: 6.8834. Min Act: -0.1700
Data Index: 5153691 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5397. Min Range: -7.5397
Max Act: 6.8834. Min Act: -0.1700
Data Index: 8780169 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5397. Min Range: -7.5397
Max Act: 6.9147. Min Act: -0.1700
Data Index: 7773182 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5397. Min Range: -7.5397
Max Act: 6.8522. Min Act: -0.1700
Data Index: 5855278 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5397. Min Range: -7.5397
Max Act: 6.8522. Min Act: -0.1700
Data Index: 7101393 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5397. Min Range: -7.5397
Max Act: 6.8522. Min Act: -0.1700
Data Index: 2371376 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5397. Min Range: -7.5397
Max Act: 6.8209. Min Act: -0.1700
Data Index: 62811 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5397. Min Range: -7.5397
Max Act: 6.8209. Min Act: -0.1700
Data Index: 7334503 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5397. Min Range: -7.5397
Max Act: 6.8522. Min Act: -0.1700
Data Index: 8808353 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5397. Min Range: -7.5397
Max Act: 6.8209. Min Act: -0.1700
Data Index: 4314801 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5397. Min Range: -7.5397
Max Act: 6.7897. Min Act: -0.1700
Data Index: 4021187 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19