Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3281 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.6500. Min Act: -0.1700
Data Index: 6823555 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.6188. Min Act: -0.1700
Data Index: 4148006 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.6188. Min Act: -0.1700
Data Index: 38308 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.6188. Min Act: -0.1700
Data Index: 8371501 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.6188. Min Act: -0.1700
Data Index: 5377248 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.5875. Min Act: -0.1700
Data Index: 8555400 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.5563. Min Act: -0.1700
Data Index: 2916534 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.5250. Min Act: -0.1700
Data Index: 8555404 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.4625. Min Act: -0.1700
Data Index: 3789309 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.5250. Min Act: -0.1700
Data Index: 4679909 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.4938. Min Act: -0.1700
Data Index: 5660654 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.4625. Min Act: -0.1700
Data Index: 1508069 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.4938. Min Act: -0.1700
Data Index: 3310178 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.4625. Min Act: -0.1700
Data Index: 739701 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.4625. Min Act: -0.1700
Data Index: 3227208 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.4625. Min Act: -0.1700
Data Index: 8709321 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.4000. Min Act: -0.1700
Data Index: 8105845 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.3688. Min Act: -0.1700
Data Index: 3998057 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.4000. Min Act: -0.1700
Data Index: 7743762 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6500. Min Range: -5.6500
Max Act: 5.4313. Min Act: -0.1700
Data Index: 335640 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19