Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5074 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.8395. Min Act: -0.1700
Data Index: 5021897 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.7457. Min Act: -0.1700
Data Index: 5766975 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5895. Min Act: -0.1700
Data Index: 2438404 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5582. Min Act: -0.1700
Data Index: 8081398 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5270. Min Act: -0.1700
Data Index: 2344881 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.5270. Min Act: -0.1700
Data Index: 4200061 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.4957. Min Act: -0.1700
Data Index: 6266743 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.4645. Min Act: -0.1700
Data Index: 1127981 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.4332. Min Act: -0.1700
Data Index: 3943950 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.4332. Min Act: -0.1700
Data Index: 5539539 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.4332. Min Act: -0.1700
Data Index: 7372869 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.4020. Min Act: -0.1700
Data Index: 1553646 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.4020. Min Act: -0.1700
Data Index: 5365874 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.4020. Min Act: -0.1700
Data Index: 7332565 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.3707. Min Act: -0.1700
Data Index: 2833018 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.3707. Min Act: -0.1700
Data Index: 5011102 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.3395. Min Act: -0.1700
Data Index: 606737 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.3395. Min Act: -0.1700
Data Index: 3968960 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.3082. Min Act: -0.1700
Data Index: 3552378 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8395. Min Range: -4.8395
Max Act: 4.3082. Min Act: -0.1700
Data Index: 447650 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19