Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5313 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.4840. Min Act: -0.1700
Data Index: 5913637 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.3902. Min Act: -0.1700
Data Index: 6664476 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.4215. Min Act: -0.1700
Data Index: 4548646 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.4527. Min Act: -0.1700
Data Index: 5602635 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.3902. Min Act: -0.1700
Data Index: 3562774 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.3902. Min Act: -0.1700
Data Index: 3109250 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.3590. Min Act: -0.1700
Data Index: 3109251 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.3590. Min Act: -0.1700
Data Index: 6664475 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.3277. Min Act: -0.1700
Data Index: 2616471 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.3277. Min Act: -0.1700
Data Index: 7407411 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.2965. Min Act: -0.1700
Data Index: 7864695 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.2965. Min Act: -0.1700
Data Index: 8448221 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.3277. Min Act: -0.1700
Data Index: 8701555 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.2652. Min Act: -0.1700
Data Index: 5602634 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.2652. Min Act: -0.1700
Data Index: 3658902 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.2652. Min Act: -0.1700
Data Index: 3101450 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.2340. Min Act: -0.1700
Data Index: 3232930 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.2340. Min Act: -0.1700
Data Index: 7864693 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.2340. Min Act: -0.1700
Data Index: 7864694 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4840. Min Range: -4.4840
Max Act: 4.2340. Min Act: -0.1700
Data Index: 1882187 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19