Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2809. Min Range: -5.2809
Max Act: 5.2809. Min Act: -0.1700
Data Index: 627722 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2809. Min Range: -5.2809
Max Act: 5.1247. Min Act: -0.1700
Data Index: 1596973 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2809. Min Range: -5.2809
Max Act: 5.0934. Min Act: -0.1700
Data Index: 6040861 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2809. Min Range: -5.2809
Max Act: 5.0934. Min Act: -0.1700
Data Index: 2426856 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2809. Min Range: -5.2809
Max Act: 5.0622. Min Act: -0.1700
Data Index: 3702586 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2809. Min Range: -5.2809
Max Act: 5.0309. Min Act: -0.1700
Data Index: 3213846 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.9997. Min Act: -0.1700
Data Index: 756269 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.9684. Min Act: -0.1700
Data Index: 5504320 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.9684. Min Act: -0.1700
Data Index: 1056913 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.9684. Min Act: -0.1700
Data Index: 6575046 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.9684. Min Act: -0.1700
Data Index: 1995074 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.9372. Min Act: -0.1700
Data Index: 1017356 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.9059. Min Act: -0.1700
Data Index: 2755567 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.9059. Min Act: -0.1700
Data Index: 3604498 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.9059. Min Act: -0.1700
Data Index: 3030475 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.8747. Min Act: -0.1700
Data Index: 91508 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.8747. Min Act: -0.1700
Data Index: 5074116 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.8747. Min Act: -0.1700
Data Index: 7004535 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.8747. Min Act: -0.1700
Data Index: 4100373 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.8747. Min Act: -0.1700
Data Index: 4908507 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19