Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.8190. Min Act: -0.1681
Data Index: 5019996 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.8019. Min Act: -0.0911
Data Index: 919010 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7933. Min Act: -0.1700
Data Index: 2584673 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7760. Min Act: -0.1693
Data Index: 3758408 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7760. Min Act: -0.1087
Data Index: 4683769 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7588. Min Act: -0.1449
Data Index: 7238330 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7588. Min Act: -0.1665
Data Index: 5537771 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7329. Min Act: -0.1418
Data Index: 5019998 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7329. Min Act: -0.1286
Data Index: 5709191 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7329. Min Act: -0.1547
Data Index: 779517 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7415. Min Act: -0.1436
Data Index: 8741017 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7329. Min Act: -0.0895
Data Index: 1986938 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7242. Min Act: -0.1624
Data Index: 3766241 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7242. Min Act: -0.1547
Data Index: 1293000 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7069. Min Act: -0.1593
Data Index: 3066486 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7155. Min Act: -0.1692
Data Index: 7238340 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7069. Min Act: -0.1669
Data Index: 5520979 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7069. Min Act: -0.1699
Data Index: 1543952 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7069. Min Act: -0.1192
Data Index: 3341643 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8190. Min Range: -1.8190
Max Act: 1.7069. Min Act: -0.1226
Data Index: 6116927 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19