Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3687 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7031. Min Range: -7.7031
Max Act: 7.7031. Min Act: -0.1700
Data Index: 7164438 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7031. Min Range: -7.7031
Max Act: 7.5468. Min Act: -0.1700
Data Index: 1687766 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7031. Min Range: -7.7031
Max Act: 7.3593. Min Act: -0.1700
Data Index: 6970643 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7031. Min Range: -7.7031
Max Act: 7.3593. Min Act: -0.1700
Data Index: 8184703 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7031. Min Range: -7.7031
Max Act: 7.2031. Min Act: -0.1700
Data Index: 205039 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7031. Min Range: -7.7031
Max Act: 7.1093. Min Act: -0.1700
Data Index: 2592372 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7031. Min Range: -7.7031
Max Act: 7.1406. Min Act: -0.1700
Data Index: 2507652 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7031. Min Range: -7.7031
Max Act: 7.0781. Min Act: -0.1700
Data Index: 901468 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7031. Min Range: -7.7031
Max Act: 7.0468. Min Act: -0.1700
Data Index: 3229268 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7031. Min Range: -7.7031
Max Act: 7.0156. Min Act: -0.1700
Data Index: 1883920 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7031. Min Range: -7.7031
Max Act: 6.9843. Min Act: -0.1700
Data Index: 119318 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7031. Min Range: -7.7031
Max Act: 6.9843. Min Act: -0.1700
Data Index: 4729997 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7031. Min Range: -7.7031
Max Act: 6.9531. Min Act: -0.1700
Data Index: 1550256 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7031. Min Range: -7.7031
Max Act: 6.9843. Min Act: -0.1700
Data Index: 182316 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7031. Min Range: -7.7031
Max Act: 6.9531. Min Act: -0.1700
Data Index: 3811386 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7031. Min Range: -7.7031
Max Act: 6.9531. Min Act: -0.1700
Data Index: 4388834 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7031. Min Range: -7.7031
Max Act: 6.9218. Min Act: -0.1700
Data Index: 2020695 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7031. Min Range: -7.7031
Max Act: 6.9218. Min Act: -0.1700
Data Index: 1907584 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7031. Min Range: -7.7031
Max Act: 6.8906. Min Act: -0.1700
Data Index: 5649376 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7031. Min Range: -7.7031
Max Act: 6.8593. Min Act: -0.1700
Data Index: 3866977 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19