Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 681 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.2411. Min Act: -0.0001

Data Index: 455869 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1879. Min Act: -0.0001

Data Index: 25596 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1789. Min Act: -0.0001

Data Index: 187444 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1703. Min Act: -0.0001

Data Index: 331076 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1791. Min Act: -0.0001

Data Index: 108135 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1122280 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1691. Min Act: -0.0001

Data Index: 62894 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1620. Min Act: -0.0001

Data Index: 401511 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1530. Min Act: -0.0001

Data Index: 979595 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1538. Min Act: -0.0001

Data Index: 551694 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1521. Min Act: -0.0001

Data Index: 60944 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1537. Min Act: -0.0001

Data Index: 614660 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1458. Min Act: -0.0001

Data Index: 802338 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1415. Min Act: -0.0001

Data Index: 858872 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1444. Min Act: -0.0001

Data Index: 487725 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1339. Min Act: -0.0001

Data Index: 731690 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1011285 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1423. Min Act: -0.0001

Data Index: 317152 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1361. Min Act: -0.0001

Data Index: 573261 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.2411. Min Range: -0.2411

Max Act: 0.1352. Min Act: -0.0001

Data Index: 633876 (C4 (Web Text))

Max Activating Token Index: 709