Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 40 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0434. Min Act: -0.0005

Data Index: 70027 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0436. Min Act: -0.0005

Data Index: 1117476 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0407. Min Act: -0.0005

Data Index: 788312 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0419. Min Act: -0.0005

Data Index: 809409 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0423. Min Act: -0.0005

Data Index: 798377 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0429. Min Act: -0.0005

Data Index: 614984 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0409. Min Act: -0.0005

Data Index: 1338454 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0378. Min Act: -0.0005

Data Index: 1205111 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0410. Min Act: -0.0005

Data Index: 760637 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0386. Min Act: -0.0005

Data Index: 1144670 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0371. Min Act: -0.0005

Data Index: 425464 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0405. Min Act: -0.0005

Data Index: 126635 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0394. Min Act: -0.0005

Data Index: 254905 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0388. Min Act: -0.0005

Data Index: 1198794 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0388. Min Act: -0.0005

Data Index: 222625 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0349. Min Act: -0.0005

Data Index: 1089192 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0381. Min Act: -0.0005

Data Index: 363051 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0355. Min Act: -0.0005

Data Index: 1355703 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0365. Min Act: -0.0005

Data Index: 802722 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0363. Min Act: -0.0005

Data Index: 753705 (C4 (Web Text))

Max Activating Token Index: 208