Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1089 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.7556. Min Act: -0.1700
Data Index: 1338909 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.7556. Min Act: -0.1700
Data Index: 8624939 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.4119. Min Act: -0.1700
Data Index: 722543 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.4119. Min Act: -0.1700
Data Index: 1943864 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.3494. Min Act: -0.1700
Data Index: 5386420 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.3494. Min Act: -0.1700
Data Index: 10893 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.3181. Min Act: -0.1700
Data Index: 4455621 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.2868. Min Act: -0.1700
Data Index: 1035794 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.3181. Min Act: -0.1700
Data Index: 6730899 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.3181. Min Act: -0.1700
Data Index: 6381535 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.2868. Min Act: -0.1700
Data Index: 3498391 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.2556. Min Act: -0.1700
Data Index: 1250065 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.2556. Min Act: -0.1700
Data Index: 872302 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.2243. Min Act: -0.1700
Data Index: 777393 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.1931. Min Act: -0.1700
Data Index: 5946106 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.2243. Min Act: -0.1700
Data Index: 221612 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.1618. Min Act: -0.1700
Data Index: 1862969 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.1931. Min Act: -0.1700
Data Index: 7607029 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.1931. Min Act: -0.1700
Data Index: 7960220 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7556. Min Range: -4.7556
Max Act: 4.2243. Min Act: -0.1700
Data Index: 1730167 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19