Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3868 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.6961. Min Act: -0.1700
Data Index: 2736544 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.6641. Min Act: -0.1700
Data Index: 822039 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.6480. Min Act: -0.1700
Data Index: 8338736 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.6320. Min Act: -0.1697
Data Index: 2644291 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.6320. Min Act: -0.1700
Data Index: 8338725 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.5998. Min Act: -0.1700
Data Index: 2644292 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.5998. Min Act: -0.1700
Data Index: 6185824 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.5837. Min Act: -0.1700
Data Index: 1983466 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.5998. Min Act: -0.1700
Data Index: 3395036 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.5837. Min Act: -0.1700
Data Index: 2644290 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.5676. Min Act: -0.1700
Data Index: 8428425 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.5676. Min Act: -0.1700
Data Index: 8338735 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.5353. Min Act: -0.1698
Data Index: 4658597 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.5353. Min Act: -0.1700
Data Index: 8309528 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.5353. Min Act: -0.1700
Data Index: 8207906 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.5191. Min Act: -0.1700
Data Index: 1780780 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.5191. Min Act: -0.1700
Data Index: 4658592 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.5353. Min Act: -0.1700
Data Index: 8338724 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.5029. Min Act: -0.1699
Data Index: 1502388 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6961. Min Range: -2.6961
Max Act: 2.5191. Min Act: -0.1698
Data Index: 7453573 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19