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

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

Neuron 5105 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.3324. Min Act: -0.0002

Data Index: 507244 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.3139. Min Act: -0.0002

Data Index: 727663 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2813. Min Act: -0.0002

Data Index: 1115287 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2715. Min Act: -0.0002

Data Index: 7809 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2741. Min Act: -0.0002

Data Index: 47732 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2643. Min Act: -0.0002

Data Index: 1352719 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2656. Min Act: -0.0002

Data Index: 648456 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2647. Min Act: -0.0002

Data Index: 195925 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2359. Min Act: -0.0002

Data Index: 99574 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2247. Min Act: -0.0002

Data Index: 1345699 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2172. Min Act: -0.0002

Data Index: 1257338 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2243. Min Act: -0.0002

Data Index: 910611 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2120. Min Act: -0.0002

Data Index: 735263 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2206. Min Act: -0.0002

Data Index: 1098341 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2129. Min Act: -0.0002

Data Index: 234311 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2207. Min Act: -0.0002

Data Index: 959309 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2069. Min Act: -0.0002

Data Index: 1358080 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.1926. Min Act: -0.0002

Data Index: 504699 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2048. Min Act: -0.0002

Data Index: 585725 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2199. Min Act: -0.0002

Data Index: 1246302 (C4 (Web Text))

Max Activating Token Index: 769