Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.3683. Min Act: -0.1700
Data Index: 6138872 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.3371. Min Act: -0.1700
Data Index: 2334974 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.3058. Min Act: -0.1700
Data Index: 3881567 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.3058. Min Act: -0.1700
Data Index: 8197787 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.3058. Min Act: -0.1700
Data Index: 455557 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.3371. Min Act: -0.1700
Data Index: 6696314 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.2433. Min Act: -0.1700
Data Index: 583372 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.2746. Min Act: -0.1700
Data Index: 2308669 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.2746. Min Act: -0.1700
Data Index: 4693447 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.2433. Min Act: -0.1700
Data Index: 4719417 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.2433. Min Act: -0.1700
Data Index: 4717940 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.2433. Min Act: -0.1700
Data Index: 1786267 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.2121. Min Act: -0.1700
Data Index: 553791 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.2433. Min Act: -0.1700
Data Index: 1332877 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.2433. Min Act: -0.1700
Data Index: 4134855 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.2433. Min Act: -0.1700
Data Index: 8092232 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.2433. Min Act: -0.1700
Data Index: 873608 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.2121. Min Act: -0.1700
Data Index: 424081 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.2121. Min Act: -0.1700
Data Index: 7673645 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3683. Min Range: -4.3683
Max Act: 4.2121. Min Act: -0.1700
Data Index: 1515281 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19