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

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

Neuron 175 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0403. Min Act: -0.0006

Data Index: 1288040 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0317. Min Act: -0.0006

Data Index: 5488 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0303. Min Act: -0.0006

Data Index: 791616 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0309. Min Act: -0.0006

Data Index: 256184 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0298. Min Act: -0.0006

Data Index: 1161046 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0302. Min Act: -0.0006

Data Index: 493339 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1292655 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0287. Min Act: -0.0006

Data Index: 646032 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0292. Min Act: -0.0006

Data Index: 1311608 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0291. Min Act: -0.0006

Data Index: 1275546 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0282. Min Act: -0.0006

Data Index: 275545 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0288. Min Act: -0.0006

Data Index: 732948 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0269. Min Act: -0.0006

Data Index: 1083523 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0287. Min Act: -0.0006

Data Index: 220561 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0272. Min Act: -0.0006

Data Index: 155159 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0300. Min Act: -0.0006

Data Index: 81954 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0293. Min Act: -0.0006

Data Index: 104067 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0298. Min Act: -0.0006

Data Index: 679018 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0283. Min Act: -0.0006

Data Index: 488255 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0276. Min Act: -0.0006

Data Index: 448228 (C4 (Web Text))

Max Activating Token Index: 103