Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5642 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.5897. Min Act: -0.1700
Data Index: 2634393 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.4647. Min Act: -0.1700
Data Index: 4122303 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.3709. Min Act: -0.1700
Data Index: 2512840 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.2772. Min Act: -0.1700
Data Index: 1352467 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.2459. Min Act: -0.1700
Data Index: 1780897 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.2147. Min Act: -0.1700
Data Index: 7948601 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.1834. Min Act: -0.1700
Data Index: 5994934 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.0897. Min Act: -0.1700
Data Index: 3125896 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.0584. Min Act: -0.1700
Data Index: 7490637 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.0584. Min Act: -0.1700
Data Index: 4170619 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.0272. Min Act: -0.1700
Data Index: 3643184 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5897. Min Range: -5.5897
Max Act: 4.9959. Min Act: -0.1700
Data Index: 2837105 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.0272. Min Act: -0.1700
Data Index: 5515583 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.0272. Min Act: -0.1700
Data Index: 6860883 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.0272. Min Act: -0.1700
Data Index: 5738326 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5897. Min Range: -5.5897
Max Act: 4.9959. Min Act: -0.1700
Data Index: 7605794 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5897. Min Range: -5.5897
Max Act: 4.9647. Min Act: -0.1700
Data Index: 295207 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5897. Min Range: -5.5897
Max Act: 4.9647. Min Act: -0.1700
Data Index: 6951944 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5897. Min Range: -5.5897
Max Act: 4.9647. Min Act: -0.1700
Data Index: 6369220 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5897. Min Range: -5.5897
Max Act: 4.9647. Min Act: -0.1700
Data Index: 5581285 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19