Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2878 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1567. Min Range: -4.1567
Max Act: 4.1567. Min Act: -0.1700
Data Index: 1384744 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1567. Min Range: -4.1567
Max Act: 4.1567. Min Act: -0.1700
Data Index: 6244511 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1567. Min Range: -4.1567
Max Act: 4.1567. Min Act: -0.1700
Data Index: 1061520 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.9691. Min Act: -0.1700
Data Index: 1601003 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.8440. Min Act: -0.1700
Data Index: 6381247 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.8440. Min Act: -0.1700
Data Index: 8257959 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.8440. Min Act: -0.1700
Data Index: 2789940 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.8440. Min Act: -0.1700
Data Index: 5036777 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.8440. Min Act: -0.1700
Data Index: 5787916 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.8128. Min Act: -0.1700
Data Index: 7951502 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.8440. Min Act: -0.1700
Data Index: 6238379 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.7815. Min Act: -0.1700
Data Index: 4889063 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.7815. Min Act: -0.1700
Data Index: 4744255 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.7815. Min Act: -0.1700
Data Index: 1096435 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.7815. Min Act: -0.1700
Data Index: 8569637 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.7502. Min Act: -0.1700
Data Index: 3482085 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.7189. Min Act: -0.1700
Data Index: 5282905 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.7502. Min Act: -0.1700
Data Index: 1370445 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.6876. Min Act: -0.1700
Data Index: 3973547 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1567. Min Range: -4.1567
Max Act: 3.6876. Min Act: -0.1700
Data Index: 966369 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19