Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2549 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.6267. Min Act: -0.1700
Data Index: 7642608 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.5642. Min Act: -0.1700
Data Index: 8631161 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.5330. Min Act: -0.1700
Data Index: 1229580 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.4392. Min Act: -0.1700
Data Index: 4829354 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.4080. Min Act: -0.1700
Data Index: 7314029 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.4080. Min Act: -0.1700
Data Index: 686461 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.4080. Min Act: -0.1700
Data Index: 3456304 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.3455. Min Act: -0.1700
Data Index: 5760615 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.3455. Min Act: -0.1700
Data Index: 5197464 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.3455. Min Act: -0.1700
Data Index: 6502560 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.2830. Min Act: -0.1700
Data Index: 1138284 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.2830. Min Act: -0.1700
Data Index: 4665797 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.2517. Min Act: -0.1700
Data Index: 2887139 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.2204. Min Act: -0.1700
Data Index: 7502607 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.2204. Min Act: -0.1700
Data Index: 6059689 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.2517. Min Act: -0.1700
Data Index: 530060 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.1892. Min Act: -0.1700
Data Index: 1081900 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.1892. Min Act: -0.1700
Data Index: 3073438 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.1892. Min Act: -0.1700
Data Index: 5885146 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6267. Min Range: -4.6267
Max Act: 4.1892. Min Act: -0.1700
Data Index: 3633453 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19