Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3734 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.3832. Min Act: -0.1700
Data Index: 7483092 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.3832. Min Act: -0.1700
Data Index: 3113635 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.3207. Min Act: -0.1700
Data Index: 5484385 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.2894. Min Act: -0.1700
Data Index: 405799 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.3207. Min Act: -0.1700
Data Index: 2735120 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.2894. Min Act: -0.1700
Data Index: 8216692 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.2582. Min Act: -0.1700
Data Index: 7904742 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.2269. Min Act: -0.1700
Data Index: 6520859 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.2269. Min Act: -0.1700
Data Index: 1988080 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.2269. Min Act: -0.1700
Data Index: 8600980 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.2269. Min Act: -0.1700
Data Index: 8578931 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.1957. Min Act: -0.1700
Data Index: 2216037 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.1957. Min Act: -0.1700
Data Index: 6478021 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.1644. Min Act: -0.1700
Data Index: 6156242 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.1644. Min Act: -0.1700
Data Index: 4917871 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.1644. Min Act: -0.1700
Data Index: 3230945 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.1644. Min Act: -0.1700
Data Index: 3866618 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.1644. Min Act: -0.1700
Data Index: 3835263 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.1644. Min Act: -0.1700
Data Index: 8424569 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3832. Min Range: -5.3832
Max Act: 5.1332. Min Act: -0.1700
Data Index: 1733862 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19