Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 684 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.1372. Min Range: -4.1372
Max Act: 4.1372. Min Act: -0.1700
Data Index: 2752553 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1372. Min Range: -4.1372
Max Act: 4.0747. Min Act: -0.1700
Data Index: 7511621 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1372. Min Range: -4.1372
Max Act: 4.0747. Min Act: -0.1700
Data Index: 2090012 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1372. Min Range: -4.1372
Max Act: 4.0122. Min Act: -0.1700
Data Index: 5328695 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.9809. Min Act: -0.1700
Data Index: 4381482 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.9809. Min Act: -0.1700
Data Index: 616769 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.9809. Min Act: -0.1700
Data Index: 567538 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.9497. Min Act: -0.1700
Data Index: 7550042 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.9497. Min Act: -0.1700
Data Index: 7686614 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.9497. Min Act: -0.1700
Data Index: 585966 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.9184. Min Act: -0.1700
Data Index: 3053444 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.9497. Min Act: -0.1700
Data Index: 6173274 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.9184. Min Act: -0.1700
Data Index: 896426 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.9184. Min Act: -0.1700
Data Index: 642057 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.9497. Min Act: -0.1700
Data Index: 2022907 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.8872. Min Act: -0.1700
Data Index: 1522182 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.8559. Min Act: -0.1700
Data Index: 7134060 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.8872. Min Act: -0.1700
Data Index: 903239 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.8872. Min Act: -0.1700
Data Index: 3300924 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1372. Min Range: -4.1372
Max Act: 3.8559. Min Act: -0.1700
Data Index: 7144736 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19