Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.7986. Min Act: -0.1700
Data Index: 4680106 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.7049. Min Act: -0.1700
Data Index: 5203429 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.7049. Min Act: -0.1700
Data Index: 4743691 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.7049. Min Act: -0.1700
Data Index: 1834089 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.6736. Min Act: -0.1700
Data Index: 2810433 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.6736. Min Act: -0.1700
Data Index: 4656580 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.6736. Min Act: -0.1700
Data Index: 4694209 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.6736. Min Act: -0.1700
Data Index: 7074321 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.6424. Min Act: -0.1700
Data Index: 120232 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.6424. Min Act: -0.1700
Data Index: 7634808 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.6424. Min Act: -0.1700
Data Index: 4454914 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.6736. Min Act: -0.1700
Data Index: 859750 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.6424. Min Act: -0.1700
Data Index: 5399435 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.6111. Min Act: -0.1700
Data Index: 2179534 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.6111. Min Act: -0.1700
Data Index: 7301014 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.6111. Min Act: -0.1700
Data Index: 8644859 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.5799. Min Act: -0.1700
Data Index: 4891499 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.6111. Min Act: -0.1700
Data Index: 1044373 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.5799. Min Act: -0.1700
Data Index: 7390578 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.5799. Min Act: -0.1700
Data Index: 4343684 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19