Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3522 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.5016. Min Act: -0.1700
Data Index: 7182781 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.4703. Min Act: -0.1700
Data Index: 6305912 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.4078. Min Act: -0.1700
Data Index: 31990 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.4078. Min Act: -0.1700
Data Index: 3847107 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.4078. Min Act: -0.1700
Data Index: 5729835 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 5786012 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 5967131 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 3680013 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 3302842 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 1290411 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 8690307 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 8079496 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 1751187 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 4054776 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 7435948 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 3755038 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 1088259 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 376803 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3453. Min Act: -0.1700
Data Index: 2592028 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5016. Min Range: -5.5016
Max Act: 5.3453. Min Act: -0.1700
Data Index: 717511 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19