Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2379 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.9216. Min Act: -0.0000

Data Index: 126150 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.9055. Min Act: -0.0000

Data Index: 113107 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.8068. Min Act: -0.0000

Data Index: 545784 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.7688. Min Act: -0.0000

Data Index: 1061119 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.7036. Min Act: -0.0000

Data Index: 437527 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.6086. Min Act: -0.0000

Data Index: 110999 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.5244. Min Act: -0.0000

Data Index: 874809 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.5167. Min Act: -0.0000

Data Index: 419414 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.4788. Min Act: -0.0000

Data Index: 343779 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.5727. Min Act: -0.0000

Data Index: 600238 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.4042. Min Act: -0.0000

Data Index: 905127 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.3880. Min Act: -0.0000

Data Index: 550452 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.3139. Min Act: -0.0000

Data Index: 335319 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.3210. Min Act: -0.0000

Data Index: 1162682 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.2754. Min Act: -0.0000

Data Index: 350012 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.2673. Min Act: -0.0000

Data Index: 314958 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.2403. Min Act: -0.0000

Data Index: 205964 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.1227. Min Act: -0.0000

Data Index: 341575 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.2299. Min Act: -0.0000

Data Index: 747087 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.2202. Min Act: -0.0000

Data Index: 599593 (C4 (Web Text))

Max Activating Token Index: 966