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

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

Neuron 2133 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.6088. Min Act: -0.0000

Data Index: 641031 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.5566. Min Act: -0.0000

Data Index: 888391 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.4051. Min Act: -0.0000

Data Index: 340643 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.3017. Min Act: -0.0000

Data Index: 329295 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.1325. Min Act: -0.0000

Data Index: 1132271 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.1776. Min Act: -0.0000

Data Index: 32893 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.2241. Min Act: -0.0000

Data Index: 995329 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.1341. Min Act: -0.0000

Data Index: 28348 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.1226. Min Act: -0.0000

Data Index: 1311915 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.1457. Min Act: -0.0000

Data Index: 434661 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.1031. Min Act: -0.0000

Data Index: 365184 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.0791. Min Act: -0.0000

Data Index: 199279 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.0916. Min Act: -0.0000

Data Index: 48778 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.0510. Min Act: -0.0000

Data Index: 1004187 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.0608. Min Act: -0.0000

Data Index: 796118 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 1.6088. Min Range: -1.6088

Max Act: 1.0201. Min Act: -0.0000

Data Index: 1143082 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 1.6088. Min Range: -1.6088

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1237208 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 1.6088. Min Range: -1.6088

Max Act: 0.9658. Min Act: -0.0000

Data Index: 371815 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 1.6088. Min Range: -1.6088

Max Act: 0.9770. Min Act: -0.0000

Data Index: 927244 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 1.6088. Min Range: -1.6088

Max Act: 0.9152. Min Act: -0.0000

Data Index: 663053 (C4 (Web Text))

Max Activating Token Index: 134