Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1772 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.7337. Min Act: -0.1700
Data Index: 1053871 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.6086. Min Act: -0.1700
Data Index: 8199544 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.5929. Min Act: -0.1700
Data Index: 4281329 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.5773. Min Act: -0.1700
Data Index: 4747873 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.5147. Min Act: -0.1700
Data Index: 2411306 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.5147. Min Act: -0.1700
Data Index: 6468151 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4990. Min Act: -0.1700
Data Index: 1712441 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4833. Min Act: -0.1700
Data Index: 5389874 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4833. Min Act: -0.1700
Data Index: 4226273 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4833. Min Act: -0.1700
Data Index: 1233862 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4833. Min Act: -0.1700
Data Index: 8756406 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4520. Min Act: -0.1700
Data Index: 331939 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4363. Min Act: -0.1700
Data Index: 119381 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4520. Min Act: -0.1700
Data Index: 5814133 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4050. Min Act: -0.1700
Data Index: 2847362 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4520. Min Act: -0.1700
Data Index: 4360006 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4363. Min Act: -0.1700
Data Index: 3231415 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4206. Min Act: -0.1700
Data Index: 3121698 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4520. Min Act: -0.1700
Data Index: 1979159 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4363. Min Act: -0.1700
Data Index: 672140 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19