Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.3890. Min Act: -0.1700
Data Index: 7484906 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.3890. Min Act: -0.1700
Data Index: 7443233 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.3578. Min Act: -0.1700
Data Index: 2823820 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.3890. Min Act: -0.1700
Data Index: 4236406 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.3578. Min Act: -0.1700
Data Index: 2386599 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.3578. Min Act: -0.1700
Data Index: 3320993 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.3265. Min Act: -0.1700
Data Index: 8318876 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.2953. Min Act: -0.1700
Data Index: 3066786 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.2953. Min Act: -0.1700
Data Index: 1281593 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.2640. Min Act: -0.1700
Data Index: 6413746 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.2640. Min Act: -0.1700
Data Index: 4997211 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.2328. Min Act: -0.1700
Data Index: 5355100 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.2640. Min Act: -0.1700
Data Index: 797819 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.2640. Min Act: -0.1700
Data Index: 130083 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.2328. Min Act: -0.1700
Data Index: 2935393 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.2328. Min Act: -0.1700
Data Index: 5842213 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.2328. Min Act: -0.1700
Data Index: 104930 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.2328. Min Act: -0.1700
Data Index: 5572997 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.2328. Min Act: -0.1700
Data Index: 3338815 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3890. Min Range: -5.3890
Max Act: 5.2015. Min Act: -0.1700
Data Index: 3408532 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19