Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 726 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.8639. Min Act: -0.1700
Data Index: 5715172 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.5823. Min Act: -0.1700
Data Index: 5952723 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.5823. Min Act: -0.1700
Data Index: 4848219 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.5040. Min Act: -0.1700
Data Index: 489602 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.4883. Min Act: -0.1700
Data Index: 6410547 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.4570. Min Act: -0.1700
Data Index: 3254187 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.4257. Min Act: -0.1700
Data Index: 6021942 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.3943. Min Act: -0.1700
Data Index: 6514073 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.3943. Min Act: -0.1700
Data Index: 7607312 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.3786. Min Act: -0.1700
Data Index: 364828 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.3943. Min Act: -0.1700
Data Index: 6549980 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.3786. Min Act: -0.1700
Data Index: 5702986 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.3786. Min Act: -0.1700
Data Index: 5900687 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.3786. Min Act: -0.1700
Data Index: 6308673 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.3786. Min Act: -0.1700
Data Index: 5610563 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.3786. Min Act: -0.1700
Data Index: 1078800 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.3629. Min Act: -0.1700
Data Index: 1848229 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.3473. Min Act: -0.1700
Data Index: 6422947 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.3629. Min Act: -0.1700
Data Index: 5199575 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8639. Min Range: -3.8639
Max Act: 3.3316. Min Act: -0.1700
Data Index: 2245807 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19