Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1604. Min Range: -5.1604
Max Act: 5.1604. Min Act: -0.1700
Data Index: 3526679 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.9104. Min Act: -0.1700
Data Index: 889678 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.8792. Min Act: -0.1700
Data Index: 3229192 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.8792. Min Act: -0.1699
Data Index: 1535376 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.8479. Min Act: -0.1700
Data Index: 3863241 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.7854. Min Act: -0.1700
Data Index: 278 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.8167. Min Act: -0.1700
Data Index: 6662133 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.7854. Min Act: -0.1700
Data Index: 1918653 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.7854. Min Act: -0.1700
Data Index: 4195179 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.7542. Min Act: -0.1700
Data Index: 5876522 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.7229. Min Act: -0.1700
Data Index: 5258707 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.7542. Min Act: -0.1700
Data Index: 4419568 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.7229. Min Act: -0.1700
Data Index: 2386810 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.7542. Min Act: -0.1700
Data Index: 3565013 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.7542. Min Act: -0.1700
Data Index: 7253697 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.7229. Min Act: -0.1700
Data Index: 443729 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.6917. Min Act: -0.1700
Data Index: 2572141 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.7229. Min Act: -0.1700
Data Index: 479583 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.7229. Min Act: -0.1700
Data Index: 4986936 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1604. Min Range: -5.1604
Max Act: 4.7229. Min Act: -0.1700
Data Index: 1441562 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19