Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 70 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.7510. Min Act: -0.1700
Data Index: 7639069 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.7510. Min Act: -0.1700
Data Index: 7624494 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.7031. Min Act: -0.1700
Data Index: 8267826 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6870. Min Act: -0.1700
Data Index: 8238762 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.7031. Min Act: -0.1700
Data Index: 889405 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6870. Min Act: -0.1700
Data Index: 2983110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6710. Min Act: -0.1700
Data Index: 5950258 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6550. Min Act: -0.1700
Data Index: 6504147 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6710. Min Act: -0.1700
Data Index: 7524915 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6550. Min Act: -0.1700
Data Index: 6212180 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6550. Min Act: -0.1700
Data Index: 7936812 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6550. Min Act: -0.1700
Data Index: 2979991 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6550. Min Act: -0.1700
Data Index: 7479747 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6550. Min Act: -0.1700
Data Index: 5444055 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6550. Min Act: -0.1700
Data Index: 1742029 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6550. Min Act: -0.1700
Data Index: 8354443 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6389. Min Act: -0.1700
Data Index: 7622207 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6389. Min Act: -0.1700
Data Index: 1070612 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6389. Min Act: -0.1700
Data Index: 1366646 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7510. Min Range: -2.7510
Max Act: 2.6389. Min Act: -0.1700
Data Index: 6569284 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19