Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 720 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.5696. Min Act: -0.1700
Data Index: 5964368 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.5383. Min Act: -0.1700
Data Index: 4095243 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.5071. Min Act: -0.1700
Data Index: 1244550 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.5071. Min Act: -0.1700
Data Index: 100210 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.5071. Min Act: -0.1700
Data Index: 6285397 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.4446. Min Act: -0.1700
Data Index: 8238802 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.3821. Min Act: -0.1700
Data Index: 5859462 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.3508. Min Act: -0.1700
Data Index: 8437706 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.3195. Min Act: -0.1700
Data Index: 3399095 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.3508. Min Act: -0.1700
Data Index: 6710063 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.3195. Min Act: -0.1700
Data Index: 2302242 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.2883. Min Act: -0.1700
Data Index: 2464512 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.2883. Min Act: -0.1700
Data Index: 161071 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.2883. Min Act: -0.1700
Data Index: 5169139 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.2570. Min Act: -0.1700
Data Index: 5169138 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.2570. Min Act: -0.1700
Data Index: 2769037 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.2258. Min Act: -0.1700
Data Index: 1416766 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.2258. Min Act: -0.1700
Data Index: 4138371 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.1945. Min Act: -0.1700
Data Index: 7196918 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5696. Min Range: -4.5696
Max Act: 4.1945. Min Act: -0.1700
Data Index: 7988884 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19