Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3843 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.6756. Min Act: -0.1700
Data Index: 2299656 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.6443. Min Act: -0.1700
Data Index: 3652125 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.4881. Min Act: -0.1700
Data Index: 1357708 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.5193. Min Act: -0.1700
Data Index: 7798188 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.4881. Min Act: -0.1700
Data Index: 2723781 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.3631. Min Act: -0.1700
Data Index: 8613635 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.3631. Min Act: -0.1700
Data Index: 8267238 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.3318. Min Act: -0.1700
Data Index: 2526210 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.2693. Min Act: -0.1700
Data Index: 6042918 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.2693. Min Act: -0.1700
Data Index: 2239888 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.2381. Min Act: -0.1700
Data Index: 5482633 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.2068. Min Act: -0.1700
Data Index: 5185414 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.2068. Min Act: -0.1700
Data Index: 5737000 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.2068. Min Act: -0.1700
Data Index: 6396457 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.1756. Min Act: -0.1700
Data Index: 999005 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.1756. Min Act: -0.1700
Data Index: 2731053 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.1443. Min Act: -0.1700
Data Index: 4377072 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.1443. Min Act: -0.1700
Data Index: 1118366 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.1443. Min Act: -0.1700
Data Index: 5627259 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6756. Min Range: -7.6756
Max Act: 7.1131. Min Act: -0.1700
Data Index: 5649004 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19