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

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

Neuron 2824 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.2796. Min Act: -0.0001

Data Index: 719517 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1232. Min Act: -0.0001

Data Index: 384992 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1337. Min Act: -0.0001

Data Index: 1250351 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.2088. Min Act: -0.0001

Data Index: 641246 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1354. Min Act: -0.0001

Data Index: 1284174 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1444. Min Act: -0.0001

Data Index: 1012870 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1367. Min Act: -0.0001

Data Index: 986339 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1246. Min Act: -0.0001

Data Index: 1304061 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0818. Min Act: -0.0001

Data Index: 572529 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0205. Min Act: -0.0001

Data Index: 1012741 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1439. Min Act: -0.0001

Data Index: 328359 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0831. Min Act: -0.0001

Data Index: 135160 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0996. Min Act: -0.0001

Data Index: 591108 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0829. Min Act: -0.0001

Data Index: 190769 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1182. Min Act: -0.0001

Data Index: 648112 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1221. Min Act: -0.0001

Data Index: 851938 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0242. Min Act: -0.0001

Data Index: 712810 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0265. Min Act: -0.0001

Data Index: 352843 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.1163. Min Act: -0.0001

Data Index: 1175852 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0551. Min Act: -0.0001

Data Index: 663764 (C4 (Web Text))

Max Activating Token Index: 58