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

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

Neuron 3529 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: 0.0404. Min Range: -0.0404

Max Act: 0.0389. Min Act: -0.0002

Data Index: 229170 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1248137 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1061294 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1234678 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0404. Min Act: -0.0002

Data Index: 186564 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0372. Min Act: -0.0002

Data Index: 682893 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1117135 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0308. Min Act: -0.0002

Data Index: 869825 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0365. Min Act: -0.0002

Data Index: 823520 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0368. Min Act: -0.0002

Data Index: 605000 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1022552 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0313. Min Act: -0.0002

Data Index: 802621 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0343. Min Act: -0.0002

Data Index: 532400 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0319. Min Act: -0.0002

Data Index: 183974 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0287. Min Act: -0.0002

Data Index: 821057 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0325. Min Act: -0.0002

Data Index: 377146 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0326. Min Act: -0.0002

Data Index: 741525 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0268. Min Act: -0.0002

Data Index: 354284 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0344. Min Act: -0.0002

Data Index: 135027 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0312. Min Act: -0.0002

Data Index: 180563 (C4 (Web Text))

Max Activating Token Index: 870