Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.5398. Min Act: -0.1700
Data Index: 4247470 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.3835. Min Act: -0.1700
Data Index: 3164775 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.4148. Min Act: -0.1700
Data Index: 3477783 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.3210. Min Act: -0.1700
Data Index: 729700 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.3210. Min Act: -0.1700
Data Index: 3894658 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.2898. Min Act: -0.1700
Data Index: 2664296 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.2585. Min Act: -0.1700
Data Index: 925611 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.2273. Min Act: -0.1700
Data Index: 7949780 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.1960. Min Act: -0.1700
Data Index: 1829157 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.1960. Min Act: -0.1700
Data Index: 5794658 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.1960. Min Act: -0.1700
Data Index: 6548842 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.1648. Min Act: -0.1700
Data Index: 4985836 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.1335. Min Act: -0.1700
Data Index: 3560090 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.1335. Min Act: -0.1700
Data Index: 2477603 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.1023. Min Act: -0.1700
Data Index: 8376421 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.1023. Min Act: -0.1700
Data Index: 1018344 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.0710. Min Act: -0.1700
Data Index: 7110398 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.0710. Min Act: -0.1700
Data Index: 7680784 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.0398. Min Act: -0.1700
Data Index: 4500110 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5398. Min Range: -7.5398
Max Act: 7.0085. Min Act: -0.1700
Data Index: 4288860 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19