Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3393 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0571. Min Range: -2.0571
Max Act: 2.0571. Min Act: -0.1700
Data Index: 1477639 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0571. Min Range: -2.0571
Max Act: 2.0065. Min Act: -0.1700
Data Index: 929166 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.9557. Min Act: -0.1700
Data Index: 8150321 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.9387. Min Act: -0.1700
Data Index: 566325 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.9047. Min Act: -0.1700
Data Index: 929162 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.9217. Min Act: -0.1700
Data Index: 4677102 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.8876. Min Act: -0.1700
Data Index: 8239918 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.8706. Min Act: -0.1700
Data Index: 8639427 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.8876. Min Act: -0.1700
Data Index: 5770349 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.8706. Min Act: -0.1700
Data Index: 929163 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.8534. Min Act: -0.1700
Data Index: 5770351 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.8706. Min Act: -0.1700
Data Index: 2066106 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.8534. Min Act: -0.1700
Data Index: 1477637 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.8363. Min Act: -0.1700
Data Index: 4494043 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.8534. Min Act: -0.1700
Data Index: 6469938 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.8363. Min Act: -0.1700
Data Index: 5760397 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.8363. Min Act: -0.1700
Data Index: 1477586 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.8363. Min Act: -0.1700
Data Index: 1893214 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.8363. Min Act: -0.1700
Data Index: 6177828 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0571. Min Range: -2.0571
Max Act: 1.8363. Min Act: -0.1700
Data Index: 8763167 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19