Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.4323. Min Act: -0.1700
Data Index: 1568274 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.4167. Min Act: -0.1700
Data Index: 6848471 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.3539. Min Act: -0.1700
Data Index: 69997 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.3696. Min Act: -0.1700
Data Index: 1100422 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.3226. Min Act: -0.1700
Data Index: 226752 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.3382. Min Act: -0.1700
Data Index: 1128122 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.3382. Min Act: -0.1700
Data Index: 97511 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.3069. Min Act: -0.1700
Data Index: 3846311 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.3069. Min Act: -0.1700
Data Index: 890817 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.2912. Min Act: -0.1700
Data Index: 4141364 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.2283. Min Act: -0.1700
Data Index: 4496948 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.2283. Min Act: -0.1700
Data Index: 6946579 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.2283. Min Act: -0.1700
Data Index: 3691130 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.1969. Min Act: -0.1700
Data Index: 7495120 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.2126. Min Act: -0.1700
Data Index: 1592323 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.2126. Min Act: -0.1700
Data Index: 5248250 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.2126. Min Act: -0.1700
Data Index: 5097885 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.2126. Min Act: -0.1700
Data Index: 8001856 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.1969. Min Act: -0.1700
Data Index: 6276011 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4323. Min Range: -3.4323
Max Act: 3.2126. Min Act: -0.1700
Data Index: 6843116 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19