Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 152 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.5197. Min Act: -0.1700
Data Index: 2528871 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.4385. Min Act: -0.1700
Data Index: 5646899 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.4548. Min Act: -0.1700
Data Index: 2931706 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.4385. Min Act: -0.1700
Data Index: 4421572 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.4223. Min Act: -0.1700
Data Index: 1408076 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.4385. Min Act: -0.1700
Data Index: 3792823 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.3733. Min Act: -0.1700
Data Index: 6109966 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.4060. Min Act: -0.1700
Data Index: 4529584 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.4060. Min Act: -0.1700
Data Index: 4427807 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.3896. Min Act: -0.1700
Data Index: 115407 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.3733. Min Act: -0.1700
Data Index: 2601876 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.3896. Min Act: -0.1700
Data Index: 3466208 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.3896. Min Act: -0.1700
Data Index: 733153 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.3405. Min Act: -0.1700
Data Index: 5260767 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.3405. Min Act: -0.1700
Data Index: 6275351 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.3405. Min Act: -0.1700
Data Index: 5599525 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.3077. Min Act: -0.1700
Data Index: 1420279 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.3241. Min Act: -0.1700
Data Index: 4373397 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.3077. Min Act: -0.1700
Data Index: 6486833 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5197. Min Range: -2.5197
Max Act: 2.2912. Min Act: -0.1700
Data Index: 6038737 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19