Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6378 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3685. Min Range: -8.3685
Max Act: 8.3685. Min Act: -0.1700
Data Index: 4818806 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3685. Min Range: -8.3685
Max Act: 8.3685. Min Act: -0.1700
Data Index: 1327551 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3685. Min Range: -8.3685
Max Act: 8.2435. Min Act: -0.1700
Data Index: 765312 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3685. Min Range: -8.3685
Max Act: 8.2435. Min Act: -0.1700
Data Index: 4550573 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3685. Min Range: -8.3685
Max Act: 8.0560. Min Act: -0.1700
Data Index: 2005015 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3685. Min Range: -8.3685
Max Act: 8.1185. Min Act: -0.1700
Data Index: 3054443 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3685. Min Range: -8.3685
Max Act: 7.9935. Min Act: -0.1700
Data Index: 5064553 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3685. Min Range: -8.3685
Max Act: 7.9935. Min Act: -0.1700
Data Index: 3786223 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3685. Min Range: -8.3685
Max Act: 7.9935. Min Act: -0.1700
Data Index: 3816161 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3685. Min Range: -8.3685
Max Act: 7.9935. Min Act: -0.1700
Data Index: 4352768 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3685. Min Range: -8.3685
Max Act: 7.9310. Min Act: -0.1700
Data Index: 4673547 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3685. Min Range: -8.3685
Max Act: 7.9310. Min Act: -0.1700
Data Index: 4528139 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3685. Min Range: -8.3685
Max Act: 7.8685. Min Act: -0.1700
Data Index: 1578549 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3685. Min Range: -8.3685
Max Act: 7.9310. Min Act: -0.1700
Data Index: 3888304 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3685. Min Range: -8.3685
Max Act: 7.9310. Min Act: -0.1700
Data Index: 1529001 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3685. Min Range: -8.3685
Max Act: 7.9310. Min Act: -0.1700
Data Index: 6787102 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3685. Min Range: -8.3685
Max Act: 7.9310. Min Act: -0.1700
Data Index: 5400345 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3685. Min Range: -8.3685
Max Act: 7.9310. Min Act: -0.1700
Data Index: 2166022 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3685. Min Range: -8.3685
Max Act: 7.8685. Min Act: -0.1700
Data Index: 636976 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3685. Min Range: -8.3685
Max Act: 7.8685. Min Act: -0.1700
Data Index: 4154949 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19