Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.6394. Min Act: -0.1700
Data Index: 701240 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.6082. Min Act: -0.1700
Data Index: 2913339 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.5457. Min Act: -0.1700
Data Index: 4624156 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.5457. Min Act: -0.1700
Data Index: 2200325 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.4832. Min Act: -0.1700
Data Index: 8007284 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.4832. Min Act: -0.1700
Data Index: 6054362 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.4832. Min Act: -0.1700
Data Index: 8828014 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.4832. Min Act: -0.1700
Data Index: 4301884 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.4519. Min Act: -0.1700
Data Index: 8205587 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.3582. Min Act: -0.1700
Data Index: 5996348 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.3894. Min Act: -0.1700
Data Index: 6350299 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.3894. Min Act: -0.1700
Data Index: 2766000 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.3894. Min Act: -0.1700
Data Index: 8443719 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.3582. Min Act: -0.1700
Data Index: 6460455 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.3582. Min Act: -0.1700
Data Index: 30130 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.3582. Min Act: -0.1700
Data Index: 4406080 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.3582. Min Act: -0.1700
Data Index: 8189421 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.3269. Min Act: -0.1700
Data Index: 904716 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.3582. Min Act: -0.1700
Data Index: 1524344 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6394. Min Range: -4.6394
Max Act: 4.3582. Min Act: -0.1700
Data Index: 7907896 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19