Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 453 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.0185. Min Range: -8.0185

Max Act: 7.7318. Min Act: -0.0000

Data Index: 759233 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 8.0185. Min Range: -8.0185

Max Act: 7.3694. Min Act: -0.0000

Data Index: 1301622 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 8.0185. Min Range: -8.0185

Max Act: 8.0185. Min Act: -0.0000

Data Index: 622845 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 8.0185. Min Range: -8.0185

Max Act: 7.5543. Min Act: -0.0000

Data Index: 517507 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 8.0185. Min Range: -8.0185

Max Act: 7.1748. Min Act: -0.0000

Data Index: 934379 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 8.0185. Min Range: -8.0185

Max Act: 7.1279. Min Act: -0.0000

Data Index: 601270 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 8.0185. Min Range: -8.0185

Max Act: 7.0619. Min Act: -0.0000

Data Index: 312687 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 8.0185. Min Range: -8.0185

Max Act: 7.2169. Min Act: -0.0000

Data Index: 334309 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 8.0185. Min Range: -8.0185

Max Act: 6.7972. Min Act: -0.0000

Data Index: 37616 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 8.0185. Min Range: -8.0185

Max Act: 7.2628. Min Act: -0.0000

Data Index: 1278044 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 8.0185. Min Range: -8.0185

Max Act: 6.6841. Min Act: -0.0000

Data Index: 278586 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 8.0185. Min Range: -8.0185

Max Act: 7.0044. Min Act: -0.0000

Data Index: 722750 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 8.0185. Min Range: -8.0185

Max Act: 6.8023. Min Act: -0.0000

Data Index: 770816 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 8.0185. Min Range: -8.0185

Max Act: 6.7880. Min Act: -0.0000

Data Index: 699362 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 8.0185. Min Range: -8.0185

Max Act: 7.1071. Min Act: -0.0000

Data Index: 1112360 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 8.0185. Min Range: -8.0185

Max Act: 6.9131. Min Act: -0.0000

Data Index: 741173 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 8.0185. Min Range: -8.0185

Max Act: 6.8906. Min Act: -0.0000

Data Index: 892856 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 8.0185. Min Range: -8.0185

Max Act: 6.8781. Min Act: -0.0000

Data Index: 997832 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 8.0185. Min Range: -8.0185

Max Act: 6.8810. Min Act: -0.0000

Data Index: 1109546 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 8.0185. Min Range: -8.0185

Max Act: 7.0206. Min Act: -0.0000

Data Index: 1016517 (C4 (Web Text))

Max Activating Token Index: 278