Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 853 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.3890. Min Act: -0.1700
Data Index: 1332786 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.3265. Min Act: -0.1700
Data Index: 8791200 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.2328. Min Act: -0.1700
Data Index: 3477434 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.2015. Min Act: -0.1700
Data Index: 4299418 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1703. Min Act: -0.1700
Data Index: 6166432 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1703. Min Act: -0.1700
Data Index: 4533102 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1703. Min Act: -0.1700
Data Index: 5671529 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1390. Min Act: -0.1700
Data Index: 2912636 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1390. Min Act: -0.1700
Data Index: 7450379 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1077. Min Act: -0.1700
Data Index: 5419868 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1077. Min Act: -0.1700
Data Index: 4854329 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.0765. Min Act: -0.1700
Data Index: 5522821 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.0765. Min Act: -0.1700
Data Index: 919438 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.0765. Min Act: -0.1700
Data Index: 2382369 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.0765. Min Act: -0.1700
Data Index: 6780599 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.0765. Min Act: -0.1700
Data Index: 6098345 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.0452. Min Act: -0.1700
Data Index: 1077074 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.0452. Min Act: -0.1700
Data Index: 1768948 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.0452. Min Act: -0.1700
Data Index: 6567405 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.0452. Min Act: -0.1700
Data Index: 4531658 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19