Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 891 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0288. Min Range: -9.0288
Max Act: 9.0288. Min Act: -0.1700
Data Index: 6481263 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0288. Min Range: -9.0288
Max Act: 9.0288. Min Act: -0.1700
Data Index: 631388 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.9038. Min Act: -0.1700
Data Index: 6259235 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.6538. Min Act: -0.1700
Data Index: 5108232 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.5288. Min Act: -0.1700
Data Index: 5599684 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.4663. Min Act: -0.1700
Data Index: 4566256 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.4663. Min Act: -0.1700
Data Index: 1742265 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.4038. Min Act: -0.1700
Data Index: 3768853 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.4038. Min Act: -0.1700
Data Index: 6522492 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.4038. Min Act: -0.1700
Data Index: 2339894 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.3413. Min Act: -0.1700
Data Index: 3520960 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.3413. Min Act: -0.1700
Data Index: 1248927 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.2788. Min Act: -0.1700
Data Index: 4523501 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.2788. Min Act: -0.1700
Data Index: 5376586 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.2788. Min Act: -0.1700
Data Index: 3933639 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.2163. Min Act: -0.1700
Data Index: 1636657 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.2163. Min Act: -0.1700
Data Index: 1965406 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.2788. Min Act: -0.1700
Data Index: 6481261 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.2788. Min Act: -0.1700
Data Index: 1700600 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0288. Min Range: -9.0288
Max Act: 8.1538. Min Act: -0.1700
Data Index: 2111301 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19