Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2684 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6198. Min Range: -5.6198
Max Act: 5.6198. Min Act: -0.1700
Data Index: 462538 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6198. Min Range: -5.6198
Max Act: 5.3073. Min Act: -0.1700
Data Index: 6505483 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6198. Min Range: -5.6198
Max Act: 5.3073. Min Act: -0.1700
Data Index: 7689570 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6198. Min Range: -5.6198
Max Act: 5.2448. Min Act: -0.1700
Data Index: 682236 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6198. Min Range: -5.6198
Max Act: 5.2448. Min Act: -0.1700
Data Index: 2271522 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6198. Min Range: -5.6198
Max Act: 5.2136. Min Act: -0.1700
Data Index: 4217093 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6198. Min Range: -5.6198
Max Act: 5.1823. Min Act: -0.1700
Data Index: 5684548 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6198. Min Range: -5.6198
Max Act: 5.1823. Min Act: -0.1700
Data Index: 404407 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6198. Min Range: -5.6198
Max Act: 5.0261. Min Act: -0.1700
Data Index: 8535917 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6198. Min Range: -5.6198
Max Act: 5.0261. Min Act: -0.1700
Data Index: 4935327 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6198. Min Range: -5.6198
Max Act: 5.0261. Min Act: -0.1700
Data Index: 8259405 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6198. Min Range: -5.6198
Max Act: 4.9948. Min Act: -0.1700
Data Index: 2439018 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6198. Min Range: -5.6198
Max Act: 4.9636. Min Act: -0.1700
Data Index: 3889172 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6198. Min Range: -5.6198
Max Act: 4.9323. Min Act: -0.1700
Data Index: 3119643 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6198. Min Range: -5.6198
Max Act: 4.9323. Min Act: -0.1700
Data Index: 2358906 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6198. Min Range: -5.6198
Max Act: 4.9323. Min Act: -0.1700
Data Index: 1992961 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6198. Min Range: -5.6198
Max Act: 4.9323. Min Act: -0.1700
Data Index: 3166989 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6198. Min Range: -5.6198
Max Act: 4.8698. Min Act: -0.1700
Data Index: 5788778 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6198. Min Range: -5.6198
Max Act: 4.8698. Min Act: -0.1700
Data Index: 2965019 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6198. Min Range: -5.6198
Max Act: 4.8698. Min Act: -0.1700
Data Index: 5942785 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19