Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 456 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.1452. Min Act: -0.1700
Data Index: 5460421 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0515. Min Act: -0.1700
Data Index: 696740 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0202. Min Act: -0.1700
Data Index: 2352932 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0202. Min Act: -0.1700
Data Index: 684375 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0202. Min Act: -0.1700
Data Index: 6798162 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0202. Min Act: -0.1700
Data Index: 4517159 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0515. Min Act: -0.1700
Data Index: 631417 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0202. Min Act: -0.1700
Data Index: 560797 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.9577. Min Act: -0.1700
Data Index: 4780465 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.9577. Min Act: -0.1700
Data Index: 1494739 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.9577. Min Act: -0.1700
Data Index: 6498763 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.9265. Min Act: -0.1700
Data Index: 7940824 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.9577. Min Act: -0.1700
Data Index: 955223 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.8952. Min Act: -0.1700
Data Index: 7949253 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.9265. Min Act: -0.1700
Data Index: 5835041 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.8952. Min Act: -0.1700
Data Index: 226267 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.9577. Min Act: -0.1700
Data Index: 844440 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.8952. Min Act: -0.1700
Data Index: 64538 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.8952. Min Act: -0.1700
Data Index: 2055767 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.8640. Min Act: -0.1700
Data Index: 3317023 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19