Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1781 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.8394. Min Act: -0.1700
Data Index: 8185985 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.8238. Min Act: -0.1700
Data Index: 4655473 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.5578. Min Act: -0.1700
Data Index: 12563 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.5422. Min Act: -0.1700
Data Index: 6429380 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.5422. Min Act: -0.1700
Data Index: 3739722 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.5422. Min Act: -0.1700
Data Index: 7218228 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.4952. Min Act: -0.1700
Data Index: 1078246 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.4639. Min Act: -0.1700
Data Index: 6955912 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.4482. Min Act: -0.1700
Data Index: 3881691 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.4325. Min Act: -0.1700
Data Index: 95686 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.4482. Min Act: -0.1700
Data Index: 40864 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.4639. Min Act: -0.1700
Data Index: 1493785 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.3855. Min Act: -0.1700
Data Index: 1746737 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.4012. Min Act: -0.1700
Data Index: 6552582 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.3698. Min Act: -0.1700
Data Index: 5406896 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.3698. Min Act: -0.1700
Data Index: 2309826 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.3698. Min Act: -0.1700
Data Index: 1038045 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.3855. Min Act: -0.1700
Data Index: 3372347 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.3541. Min Act: -0.1700
Data Index: 2954567 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8394. Min Range: -3.8394
Max Act: 3.3384. Min Act: -0.1700
Data Index: 818252 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19