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

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

Neuron 1589 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1104. Min Range: -2.1104

Max Act: 2.1104. Min Act: -0.0000

Data Index: 390606 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.9936. Min Act: -0.0000

Data Index: 946 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.9410. Min Act: -0.0000

Data Index: 1292664 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.7030. Min Act: -0.0000

Data Index: 340331 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.6790. Min Act: -0.0000

Data Index: 231431 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.6572. Min Act: -0.0000

Data Index: 466633 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.7499. Min Act: -0.0000

Data Index: 352110 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.5415. Min Act: -0.0000

Data Index: 819483 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.4655. Min Act: -0.0000

Data Index: 621946 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.4515. Min Act: -0.0000

Data Index: 1020885 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.4252. Min Act: -0.0001

Data Index: 903856 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.4215. Min Act: -0.0000

Data Index: 959773 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.4246. Min Act: -0.0000

Data Index: 643019 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.4402. Min Act: -0.0000

Data Index: 279645 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.3653. Min Act: -0.0000

Data Index: 798275 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.3221. Min Act: -0.0000

Data Index: 852348 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.3274. Min Act: -0.0000

Data Index: 1202917 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.3061. Min Act: -0.0000

Data Index: 789727 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.2910. Min Act: -0.0000

Data Index: 1352918 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 2.1104. Min Range: -2.1104

Max Act: 1.1898. Min Act: -0.0000

Data Index: 1033286 (C4 (Web Text))

Max Activating Token Index: 155