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

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

Neuron 462 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0202. Min Range: -1.0202

Max Act: 1.0202. Min Act: -0.0001

Data Index: 934010 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8886. Min Act: -0.0001

Data Index: 226572 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.9384. Min Act: -0.0001

Data Index: 787126 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8402. Min Act: -0.0001

Data Index: 264957 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8144. Min Act: -0.0001

Data Index: 1174893 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8565. Min Act: -0.0001

Data Index: 1005967 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8662. Min Act: -0.0001

Data Index: 182675 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8061. Min Act: -0.0001

Data Index: 1230766 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8903. Min Act: -0.0001

Data Index: 762199 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7954. Min Act: -0.0001

Data Index: 796952 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7839. Min Act: -0.0001

Data Index: 1263944 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8167. Min Act: -0.0001

Data Index: 814684 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7898. Min Act: -0.0001

Data Index: 113569 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8199. Min Act: -0.0001

Data Index: 1353181 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7801. Min Act: -0.0001

Data Index: 949012 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7627. Min Act: -0.0001

Data Index: 984914 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7583. Min Act: -0.0001

Data Index: 6490 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7317. Min Act: -0.0001

Data Index: 145196 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7700. Min Act: -0.0001

Data Index: 436079 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7277. Min Act: -0.0001

Data Index: 1149875 (C4 (Web Text))

Max Activating Token Index: 13