Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 435 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.6390. Min Act: -0.1700
Data Index: 2820350 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.6077. Min Act: -0.1700
Data Index: 6771504 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.5452. Min Act: -0.1700
Data Index: 8783932 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.5452. Min Act: -0.1700
Data Index: 5981636 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.5452. Min Act: -0.1700
Data Index: 3937332 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.5140. Min Act: -0.1700
Data Index: 4192822 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.4515. Min Act: -0.1700
Data Index: 8141882 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.4827. Min Act: -0.1700
Data Index: 4420239 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.4202. Min Act: -0.1700
Data Index: 3178327 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.4202. Min Act: -0.1700
Data Index: 4283161 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.4202. Min Act: -0.1700
Data Index: 6002455 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.3890. Min Act: -0.1700
Data Index: 4875007 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.4202. Min Act: -0.1700
Data Index: 8751835 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.2952. Min Act: -0.1700
Data Index: 7895411 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.2952. Min Act: -0.1700
Data Index: 254461 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.2327. Min Act: -0.1700
Data Index: 2269705 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.2327. Min Act: -0.1700
Data Index: 5118581 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.2015. Min Act: -0.1700
Data Index: 1215344 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.2015. Min Act: -0.1700
Data Index: 4930070 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6390. Min Range: -5.6390
Max Act: 5.2015. Min Act: -0.1700
Data Index: 6771503 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19