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

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

Neuron 4303 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0419. Min Act: -0.0002

Data Index: 876414 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0439. Min Act: -0.0002

Data Index: 215720 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0398. Min Act: -0.0002

Data Index: 120306 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0325. Min Act: -0.0002

Data Index: 136933 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0326. Min Act: -0.0002

Data Index: 562849 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0398. Min Act: -0.0002

Data Index: 349500 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1075740 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0338. Min Act: -0.0002

Data Index: 251825 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0314. Min Act: -0.0002

Data Index: 688352 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0369. Min Act: -0.0002

Data Index: 89315 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0347. Min Act: -0.0002

Data Index: 21131 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0326. Min Act: -0.0002

Data Index: 774422 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0330. Min Act: -0.0002

Data Index: 302187 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1329631 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0348. Min Act: -0.0002

Data Index: 643557 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0320. Min Act: -0.0002

Data Index: 465933 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0359. Min Act: -0.0002

Data Index: 942513 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0345. Min Act: -0.0002

Data Index: 905622 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0334. Min Act: -0.0002

Data Index: 605990 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1107616 (C4 (Web Text))

Max Activating Token Index: 158