Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4667 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.6476. Min Act: -0.1700
Data Index: 1780037 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.6476. Min Act: -0.1700
Data Index: 891951 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.6476. Min Act: -0.1700
Data Index: 318039 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.6476. Min Act: -0.1700
Data Index: 5364498 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.6476. Min Act: -0.1700
Data Index: 2006604 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.6164. Min Act: -0.1700
Data Index: 4015641 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.6164. Min Act: -0.1700
Data Index: 970034 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.5851. Min Act: -0.1700
Data Index: 6268226 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.5539. Min Act: -0.1700
Data Index: 1931618 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.5539. Min Act: -0.1700
Data Index: 3770576 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.5226. Min Act: -0.1700
Data Index: 7721062 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.4914. Min Act: -0.1700
Data Index: 4689271 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.5226. Min Act: -0.1700
Data Index: 7372460 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.5226. Min Act: -0.1700
Data Index: 6853067 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.4914. Min Act: -0.1700
Data Index: 7891499 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.5226. Min Act: -0.1700
Data Index: 4973414 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.4601. Min Act: -0.1700
Data Index: 4544587 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.4601. Min Act: -0.1700
Data Index: 5846597 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.4601. Min Act: -0.1700
Data Index: 2524401 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6476. Min Range: -4.6476
Max Act: 4.4601. Min Act: -0.1700
Data Index: 7048598 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19