Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3392 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8347. Min Range: -6.8347
Max Act: 6.8347. Min Act: -0.1700
Data Index: 8556318 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8347. Min Range: -6.8347
Max Act: 6.5222. Min Act: -0.1700
Data Index: 2134430 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8347. Min Range: -6.8347
Max Act: 6.3347. Min Act: -0.1700
Data Index: 5314547 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8347. Min Range: -6.8347
Max Act: 6.2722. Min Act: -0.1700
Data Index: 3433178 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8347. Min Range: -6.8347
Max Act: 6.2410. Min Act: -0.1700
Data Index: 5907515 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8347. Min Range: -6.8347
Max Act: 6.1785. Min Act: -0.1700
Data Index: 6602168 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8347. Min Range: -6.8347
Max Act: 6.1472. Min Act: -0.1700
Data Index: 918020 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8347. Min Range: -6.8347
Max Act: 6.1160. Min Act: -0.1700
Data Index: 7422475 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8347. Min Range: -6.8347
Max Act: 6.0847. Min Act: -0.1700
Data Index: 5071068 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8347. Min Range: -6.8347
Max Act: 6.0535. Min Act: -0.1700
Data Index: 6810485 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8347. Min Range: -6.8347
Max Act: 6.0222. Min Act: -0.1700
Data Index: 3595369 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8347. Min Range: -6.8347
Max Act: 6.0535. Min Act: -0.1700
Data Index: 1780909 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8347. Min Range: -6.8347
Max Act: 5.9910. Min Act: -0.1700
Data Index: 3852503 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8347. Min Range: -6.8347
Max Act: 5.9597. Min Act: -0.1700
Data Index: 5543175 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8347. Min Range: -6.8347
Max Act: 5.9597. Min Act: -0.1700
Data Index: 347811 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8347. Min Range: -6.8347
Max Act: 5.9597. Min Act: -0.1700
Data Index: 863028 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8347. Min Range: -6.8347
Max Act: 5.9910. Min Act: -0.1700
Data Index: 7297819 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8347. Min Range: -6.8347
Max Act: 5.9285. Min Act: -0.1700
Data Index: 5894218 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8347. Min Range: -6.8347
Max Act: 5.9285. Min Act: -0.1700
Data Index: 2254728 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8347. Min Range: -6.8347
Max Act: 5.9285. Min Act: -0.1700
Data Index: 7450378 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19