Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3832 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.8299. Min Act: -0.1700
Data Index: 4041609 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.6424. Min Act: -0.1700
Data Index: 8279033 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.6424. Min Act: -0.1700
Data Index: 7452064 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.5174. Min Act: -0.1700
Data Index: 3130099 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.5174. Min Act: -0.1700
Data Index: 8832162 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.5174. Min Act: -0.1700
Data Index: 505867 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.5174. Min Act: -0.1700
Data Index: 5394659 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.5174. Min Act: -0.1700
Data Index: 7065184 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.5174. Min Act: -0.1700
Data Index: 8250312 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.4549. Min Act: -0.1700
Data Index: 4165533 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.4861. Min Act: -0.1700
Data Index: 5961708 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.4549. Min Act: -0.1700
Data Index: 6212302 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.4861. Min Act: -0.1700
Data Index: 3865985 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.4861. Min Act: -0.1700
Data Index: 1971994 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.4236. Min Act: -0.1700
Data Index: 1947678 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.4236. Min Act: -0.1700
Data Index: 2702383 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.4236. Min Act: -0.1700
Data Index: 567784 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.4236. Min Act: -0.1700
Data Index: 3403241 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.4236. Min Act: -0.1700
Data Index: 1242840 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8299. Min Range: -6.8299
Max Act: 6.4236. Min Act: -0.1700
Data Index: 4715019 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19