Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4059 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.3409. Min Act: -0.1700
Data Index: 6520046 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.2784. Min Act: -0.1700
Data Index: 3177053 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.2471. Min Act: -0.1700
Data Index: 734924 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.3096. Min Act: -0.1700
Data Index: 6472265 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.2471. Min Act: -0.1700
Data Index: 167263 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.2471. Min Act: -0.1700
Data Index: 5100044 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.2159. Min Act: -0.1700
Data Index: 585923 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.2159. Min Act: -0.1700
Data Index: 4935058 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.1846. Min Act: -0.1700
Data Index: 7120799 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.1846. Min Act: -0.1700
Data Index: 7309526 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.1534. Min Act: -0.1700
Data Index: 2699795 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.1846. Min Act: -0.1700
Data Index: 5314552 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.1846. Min Act: -0.1700
Data Index: 8188064 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.1534. Min Act: -0.1700
Data Index: 8668765 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.1846. Min Act: -0.1700
Data Index: 4555552 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.1534. Min Act: -0.1700
Data Index: 8167451 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.1221. Min Act: -0.1700
Data Index: 1365257 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.1534. Min Act: -0.1700
Data Index: 3588593 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.1534. Min Act: -0.1700
Data Index: 6441916 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3409. Min Range: -4.3409
Max Act: 4.1534. Min Act: -0.1700
Data Index: 734925 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19