Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3382 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.5019. Min Act: -0.1700
Data Index: 7613523 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.4707. Min Act: -0.1700
Data Index: 3717579 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.3769. Min Act: -0.1700
Data Index: 6899371 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.3769. Min Act: -0.1700
Data Index: 6496428 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.3769. Min Act: -0.1700
Data Index: 5355823 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2519. Min Act: -0.1700
Data Index: 8379495 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2519. Min Act: -0.1700
Data Index: 6348556 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2207. Min Act: -0.1700
Data Index: 6284006 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1894. Min Act: -0.1700
Data Index: 4075973 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2207. Min Act: -0.1700
Data Index: 5238695 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2207. Min Act: -0.1700
Data Index: 6224578 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2207. Min Act: -0.1700
Data Index: 7817949 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1581. Min Act: -0.1700
Data Index: 5910720 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1894. Min Act: -0.1700
Data Index: 5742566 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1581. Min Act: -0.1700
Data Index: 1995907 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1581. Min Act: -0.1700
Data Index: 1382471 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1269. Min Act: -0.1700
Data Index: 8754082 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1581. Min Act: -0.1700
Data Index: 4153934 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1269. Min Act: -0.1700
Data Index: 5153774 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1269. Min Act: -0.1700
Data Index: 5296279 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19