Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1257 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.7325. Min Act: -0.1700
Data Index: 2261947 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.6700. Min Act: -0.1700
Data Index: 2594778 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.6388. Min Act: -0.1700
Data Index: 635066 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.5138. Min Act: -0.1700
Data Index: 3412946 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.4825. Min Act: -0.1700
Data Index: 2514220 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.4825. Min Act: -0.1700
Data Index: 3209763 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.4513. Min Act: -0.1700
Data Index: 7828618 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.4200. Min Act: -0.1700
Data Index: 3712144 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.4200. Min Act: -0.1700
Data Index: 1845508 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.4200. Min Act: -0.1700
Data Index: 8063301 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.4513. Min Act: -0.1700
Data Index: 3688231 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.3575. Min Act: -0.1700
Data Index: 1633555 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.3888. Min Act: -0.1700
Data Index: 2500327 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.3575. Min Act: -0.1700
Data Index: 6748237 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.3888. Min Act: -0.1700
Data Index: 2315317 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.3263. Min Act: -0.1700
Data Index: 5652497 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.3263. Min Act: -0.1700
Data Index: 8462948 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.2950. Min Act: -0.1700
Data Index: 4446354 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.2950. Min Act: -0.1700
Data Index: 4982108 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7325. Min Range: -6.7325
Max Act: 6.2638. Min Act: -0.1700
Data Index: 1891200 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19