Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2020 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0256. Min Range: -3.0256
Max Act: 3.0256. Min Act: -0.1700
Data Index: 7741725 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.9782. Min Act: -0.1700
Data Index: 3240492 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.9782. Min Act: -0.1700
Data Index: 5447448 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.9623. Min Act: -0.1700
Data Index: 7502215 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.9465. Min Act: -0.1700
Data Index: 5480492 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.9307. Min Act: -0.1700
Data Index: 3858705 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.9307. Min Act: -0.1700
Data Index: 7922740 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.9307. Min Act: -0.1700
Data Index: 1804384 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.9307. Min Act: -0.1700
Data Index: 6853322 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.9307. Min Act: -0.1700
Data Index: 770799 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.9148. Min Act: -0.1700
Data Index: 2061375 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.9148. Min Act: -0.1700
Data Index: 1958765 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.9148. Min Act: -0.1700
Data Index: 7697149 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.9307. Min Act: -0.1700
Data Index: 2397678 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.9148. Min Act: -0.1700
Data Index: 3968587 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.9148. Min Act: -0.1700
Data Index: 5648611 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.8990. Min Act: -0.1700
Data Index: 7562919 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.8990. Min Act: -0.1700
Data Index: 3085456 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.8990. Min Act: -0.1700
Data Index: 7249882 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0256. Min Range: -3.0256
Max Act: 2.8990. Min Act: -0.1700
Data Index: 452767 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19