Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2021 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1128298 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.9157. Min Act: -0.0001

Data Index: 1437024 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.6529. Min Act: -0.0001

Data Index: 279236 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.9100. Min Act: -0.0001

Data Index: 867411 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.9371. Min Act: -0.0001

Data Index: 474547 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.3765. Min Act: -0.0000

Data Index: 948539 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.3208. Min Act: -0.0001

Data Index: 408136 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1117160 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1194722 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.2744. Min Act: 0.0000

Data Index: 774296 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.2712. Min Act: -0.0000

Data Index: 792613 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.2003. Min Act: -0.0001

Data Index: 680790 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.1693. Min Act: -0.0000

Data Index: 90265 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.0974. Min Act: -0.0000

Data Index: 59266 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.1376. Min Act: -0.0000

Data Index: 809911 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.0863. Min Act: -0.0001

Data Index: 891594 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.1119. Min Act: 0.0000

Data Index: 417831 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.1469. Min Act: 0.0001

Data Index: 1582124 (Python Code)

Max Activating Token Index: 201

Text #18

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.1310. Min Act: 0.0000

Data Index: 746063 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.9371. Min Range: -0.9371

Max Act: 0.1258. Min Act: -0.0000

Data Index: 65163 (C4 (Web Text))

Max Activating Token Index: 25