Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3844 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1974. Min Range: -4.1974
Max Act: 4.1974. Min Act: -0.1700
Data Index: 2869641 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1974. Min Range: -4.1974
Max Act: 4.0411. Min Act: -0.1700
Data Index: 5516109 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.9786. Min Act: -0.1700
Data Index: 4207663 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1974. Min Range: -4.1974
Max Act: 4.0099. Min Act: -0.1700
Data Index: 8234235 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1974. Min Range: -4.1974
Max Act: 4.0411. Min Act: -0.1700
Data Index: 3119041 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.9786. Min Act: -0.1700
Data Index: 846347 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.9786. Min Act: -0.1700
Data Index: 1282811 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.9161. Min Act: -0.1700
Data Index: 8312236 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8848. Min Act: -0.1700
Data Index: 3993035 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8848. Min Act: -0.1700
Data Index: 8353406 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8848. Min Act: -0.1700
Data Index: 2142274 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8535. Min Act: -0.1700
Data Index: 4180451 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.9161. Min Act: -0.1700
Data Index: 5121310 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8535. Min Act: -0.1700
Data Index: 598252 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8535. Min Act: -0.1700
Data Index: 5036841 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8535. Min Act: -0.1700
Data Index: 5145376 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8223. Min Act: -0.1700
Data Index: 4044165 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8223. Min Act: -0.1700
Data Index: 487950 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.7910. Min Act: -0.1700
Data Index: 7532346 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8223. Min Act: -0.1700
Data Index: 1761489 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19