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

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

Neuron 525 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0509. Min Act: -0.0003

Data Index: 267196 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0512. Min Act: -0.0002

Data Index: 522592 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0526. Min Act: -0.0003

Data Index: 869782 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0401. Min Act: -0.0003

Data Index: 672090 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0361. Min Act: -0.0002

Data Index: 662725 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1074554 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1193053 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0348. Min Act: -0.0003

Data Index: 436381 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0349. Min Act: -0.0002

Data Index: 57695 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0347. Min Act: -0.0002

Data Index: 631382 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0357. Min Act: -0.0003

Data Index: 547372 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0346. Min Act: -0.0003

Data Index: 675753 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0354. Min Act: -0.0002

Data Index: 304824 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0339. Min Act: -0.0002

Data Index: 518711 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0313. Min Act: -0.0002

Data Index: 612762 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1148228 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1031337 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0327. Min Act: -0.0003

Data Index: 712719 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0342. Min Act: -0.0003

Data Index: 176064 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0318. Min Act: -0.0002

Data Index: 374402 (C4 (Web Text))

Max Activating Token Index: 233