Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.8678. Min Act: -0.1700
Data Index: 8218174 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.6803. Min Act: -0.1700
Data Index: 4733800 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.5240. Min Act: -0.1700
Data Index: 612099 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.4928. Min Act: -0.1700
Data Index: 7248709 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.4615. Min Act: -0.1700
Data Index: 6668540 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.4615. Min Act: -0.1700
Data Index: 7933665 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.3990. Min Act: -0.1700
Data Index: 2721296 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.3678. Min Act: -0.1700
Data Index: 2643742 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.3053. Min Act: -0.1700
Data Index: 8255901 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.2428. Min Act: -0.1700
Data Index: 3019121 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.2428. Min Act: -0.1700
Data Index: 2042976 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.1803. Min Act: -0.1700
Data Index: 1065662 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.1803. Min Act: -0.1700
Data Index: 1592990 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.2115. Min Act: -0.1700
Data Index: 209544 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.1803. Min Act: -0.1700
Data Index: 3007193 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.1803. Min Act: -0.1700
Data Index: 2468330 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.1803. Min Act: -0.1700
Data Index: 36753 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.1178. Min Act: -0.1700
Data Index: 8249898 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.1490. Min Act: -0.1700
Data Index: 1138009 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8678. Min Range: -7.8678
Max Act: 7.1490. Min Act: -0.1700
Data Index: 8731710 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19