Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2562 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.8248. Min Act: -0.1699
Data Index: 2733120 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.7623. Min Act: -0.1700
Data Index: 1489949 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.7623. Min Act: -0.1700
Data Index: 3066483 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.7623. Min Act: -0.1700
Data Index: 6438019 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.7311. Min Act: -0.1698
Data Index: 2733118 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.7311. Min Act: -0.1700
Data Index: 7644090 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.6061. Min Act: -0.1700
Data Index: 1040316 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.6061. Min Act: -0.1700
Data Index: 6290575 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.5436. Min Act: -0.1700
Data Index: 577872 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.5436. Min Act: -0.1700
Data Index: 709671 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.5123. Min Act: -0.1699
Data Index: 6439619 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.4498. Min Act: -0.1700
Data Index: 4132540 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.3873. Min Act: -0.1700
Data Index: 2332207 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.3248. Min Act: -0.1700
Data Index: 1051905 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.3248. Min Act: -0.1700
Data Index: 1060010 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.2935. Min Act: -0.1700
Data Index: 4240205 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.2935. Min Act: -0.1700
Data Index: 2404592 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.2935. Min Act: -0.1700
Data Index: 5585695 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.2935. Min Act: -0.1700
Data Index: 5809082 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8248. Min Range: -4.8248
Max Act: 4.2310. Min Act: -0.1700
Data Index: 7927123 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19