Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.9381. Min Act: -0.1700
Data Index: 4328014 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.8756. Min Act: -0.1700
Data Index: 3765975 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.8443. Min Act: -0.1700
Data Index: 3833415 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.7818. Min Act: -0.1700
Data Index: 8077985 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.7506. Min Act: -0.1700
Data Index: 916411 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.7506. Min Act: -0.1700
Data Index: 5545568 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.7193. Min Act: -0.1700
Data Index: 5055501 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.6881. Min Act: -0.1700
Data Index: 4224425 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.6881. Min Act: -0.1700
Data Index: 2214138 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.7193. Min Act: -0.1700
Data Index: 5121338 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.6881. Min Act: -0.1700
Data Index: 4629047 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.6568. Min Act: -0.1700
Data Index: 4640025 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.6568. Min Act: -0.1700
Data Index: 3154611 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.6568. Min Act: -0.1700
Data Index: 155673 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.6568. Min Act: -0.1700
Data Index: 5184366 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.6568. Min Act: -0.1700
Data Index: 7182618 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.6256. Min Act: -0.1700
Data Index: 501659 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.6256. Min Act: -0.1700
Data Index: 1565129 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.6256. Min Act: -0.1700
Data Index: 5651868 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9381. Min Range: -4.9381
Max Act: 4.6256. Min Act: -0.1700
Data Index: 3852782 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19