Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5245 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.8204. Min Act: -0.1700
Data Index: 1341198 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.8045. Min Act: -0.1700
Data Index: 4039667 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.8045. Min Act: -0.1700
Data Index: 2684382 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.8045. Min Act: -0.1700
Data Index: 2543389 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7886. Min Act: -0.1700
Data Index: 2117581 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7727. Min Act: -0.1700
Data Index: 5079952 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7727. Min Act: -0.1700
Data Index: 664803 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7727. Min Act: -0.1700
Data Index: 4005702 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7727. Min Act: -0.1700
Data Index: 6802505 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7727. Min Act: -0.1700
Data Index: 721446 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7727. Min Act: -0.1700
Data Index: 1841184 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7727. Min Act: -0.1700
Data Index: 2298269 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7567. Min Act: -0.1700
Data Index: 1357886 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7407. Min Act: -0.1700
Data Index: 5809867 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7727. Min Act: -0.1700
Data Index: 604838 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7727. Min Act: -0.1700
Data Index: 1704408 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7567. Min Act: -0.1700
Data Index: 4358007 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7567. Min Act: -0.1700
Data Index: 193324 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7407. Min Act: -0.1700
Data Index: 4103480 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8204. Min Range: -2.8204
Max Act: 2.7407. Min Act: -0.1700
Data Index: 4384889 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19