Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6016 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.9666. Min Act: -0.1700
Data Index: 6252793 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.8416. Min Act: -0.1700
Data Index: 7339881 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.7166. Min Act: -0.1700
Data Index: 5808400 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.7166. Min Act: -0.1700
Data Index: 5833089 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.5916. Min Act: -0.1700
Data Index: 21248 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.5291. Min Act: -0.1700
Data Index: 4697741 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.4978. Min Act: -0.1700
Data Index: 2722817 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.4666. Min Act: -0.1700
Data Index: 4180636 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.4666. Min Act: -0.1700
Data Index: 3568974 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.4666. Min Act: -0.1700
Data Index: 3014947 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.4353. Min Act: -0.1700
Data Index: 752180 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.4353. Min Act: -0.1700
Data Index: 8304575 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.4353. Min Act: -0.1700
Data Index: 5079050 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.4353. Min Act: -0.1700
Data Index: 7170287 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.4041. Min Act: -0.1700
Data Index: 3075837 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.4041. Min Act: -0.1700
Data Index: 6726783 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.4041. Min Act: -0.1700
Data Index: 5624637 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.3728. Min Act: -0.1700
Data Index: 7702025 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.4353. Min Act: -0.1700
Data Index: 5641477 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9666. Min Range: -4.9666
Max Act: 4.4041. Min Act: -0.1700
Data Index: 762891 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19