Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4668 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5490. Min Range: -11.5490
Max Act: 11.5490. Min Act: -0.1700
Data Index: 1599520 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5490. Min Range: -11.5490
Max Act: 11.4240. Min Act: -0.1700
Data Index: 4067 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5490. Min Range: -11.5490
Max Act: 11.2365. Min Act: -0.1700
Data Index: 5955991 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5490. Min Range: -11.5490
Max Act: 11.0490. Min Act: -0.1700
Data Index: 5655980 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.9865. Min Act: -0.1700
Data Index: 3662908 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.9865. Min Act: -0.1700
Data Index: 8371794 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.9240. Min Act: -0.1700
Data Index: 6305995 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.9240. Min Act: -0.1700
Data Index: 4929257 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.7990. Min Act: -0.1700
Data Index: 3710547 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.6740. Min Act: -0.1700
Data Index: 1669121 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.6740. Min Act: -0.1700
Data Index: 2957726 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.6115. Min Act: -0.1700
Data Index: 8693535 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.6115. Min Act: -0.1700
Data Index: 6658859 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.6115. Min Act: -0.1700
Data Index: 6819922 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.5490. Min Act: -0.1700
Data Index: 210278 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.5490. Min Act: -0.1700
Data Index: 1967993 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.5490. Min Act: -0.1700
Data Index: 7029104 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.5490. Min Act: -0.1700
Data Index: 4485504 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.5490. Min Act: -0.1700
Data Index: 7133226 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5490. Min Range: -11.5490
Max Act: 10.5490. Min Act: -0.1700
Data Index: 2607366 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19