Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.8714. Min Act: -0.1700
Data Index: 3913482 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.7777. Min Act: -0.1700
Data Index: 261451 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.7777. Min Act: -0.1700
Data Index: 3248355 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.7152. Min Act: -0.1700
Data Index: 412887 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.7152. Min Act: -0.1700
Data Index: 2909545 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.7152. Min Act: -0.1700
Data Index: 478259 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.6839. Min Act: -0.1700
Data Index: 42673 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.6214. Min Act: -0.1700
Data Index: 5701453 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.5902. Min Act: -0.1700
Data Index: 3037556 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.5589. Min Act: -0.1700
Data Index: 2900982 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.5277. Min Act: -0.1700
Data Index: 239407 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.5589. Min Act: -0.1700
Data Index: 7728284 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.4964. Min Act: -0.1700
Data Index: 4377567 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.4652. Min Act: -0.1700
Data Index: 3910873 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.4652. Min Act: -0.1700
Data Index: 4255869 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.4652. Min Act: -0.1700
Data Index: 1225752 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.4652. Min Act: -0.1700
Data Index: 6006455 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.4964. Min Act: -0.1700
Data Index: 4584018 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.4652. Min Act: -0.1700
Data Index: 6866937 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8714. Min Range: -5.8714
Max Act: 5.4652. Min Act: -0.1700
Data Index: 2731240 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19