Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3292 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.3816. Min Act: -0.1700
Data Index: 3819748 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.2566. Min Act: -0.1700
Data Index: 3238165 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.2566. Min Act: -0.1700
Data Index: 4163331 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.2254. Min Act: -0.1700
Data Index: 1308332 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.2566. Min Act: -0.1700
Data Index: 1781693 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.2566. Min Act: -0.1700
Data Index: 774409 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.2566. Min Act: -0.1700
Data Index: 4767617 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.2879. Min Act: -0.1700
Data Index: 8819115 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.1941. Min Act: -0.1700
Data Index: 8456389 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.2566. Min Act: -0.1700
Data Index: 578908 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.1941. Min Act: -0.1700
Data Index: 7795442 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.2254. Min Act: -0.1700
Data Index: 7825466 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.2254. Min Act: -0.1700
Data Index: 2779563 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.1941. Min Act: -0.1700
Data Index: 2784866 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.1941. Min Act: -0.1700
Data Index: 87935 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.1941. Min Act: -0.1700
Data Index: 6785342 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.1629. Min Act: -0.1700
Data Index: 1831931 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.1941. Min Act: -0.1700
Data Index: 7059302 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.1941. Min Act: -0.1700
Data Index: 8126360 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3816. Min Range: -4.3816
Max Act: 4.1629. Min Act: -0.1700
Data Index: 1787003 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19