Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1635 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.4373. Min Act: -0.1700
Data Index: 7315492 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3748. Min Act: -0.1700
Data Index: 1335525 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3435. Min Act: -0.1700
Data Index: 8795664 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3435. Min Act: -0.1700
Data Index: 3354846 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3435. Min Act: -0.1700
Data Index: 8434760 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3435. Min Act: -0.1700
Data Index: 4254148 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3435. Min Act: -0.1700
Data Index: 8404978 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3435. Min Act: -0.1700
Data Index: 7956157 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3435. Min Act: -0.1700
Data Index: 295528 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3435. Min Act: -0.1700
Data Index: 6862801 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3123. Min Act: -0.1700
Data Index: 339212 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3123. Min Act: -0.1700
Data Index: 6406852 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3123. Min Act: -0.1700
Data Index: 1164479 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3123. Min Act: -0.1700
Data Index: 4921947 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3123. Min Act: -0.1700
Data Index: 4410453 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3123. Min Act: -0.1700
Data Index: 4399067 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3123. Min Act: -0.1700
Data Index: 441995 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3123. Min Act: -0.1700
Data Index: 3520489 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.3123. Min Act: -0.1700
Data Index: 3024325 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4373. Min Range: -4.4373
Max Act: 4.2810. Min Act: -0.1700
Data Index: 788287 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19