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

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

Neuron 2956 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.7253. Min Act: -0.0000

Data Index: 1280934 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.4306. Min Act: -0.0000

Data Index: 327672 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.3639. Min Act: -0.0000

Data Index: 193412 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.2611. Min Act: -0.0000

Data Index: 758937 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.2553. Min Act: -0.0000

Data Index: 190915 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.2821. Min Act: -0.0000

Data Index: 1077699 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.1675. Min Act: -0.0000

Data Index: 767464 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.1656. Min Act: -0.0000

Data Index: 902839 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.3034. Min Act: -0.0000

Data Index: 810372 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.3001. Min Act: -0.0000

Data Index: 1123076 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.1966. Min Act: -0.0000

Data Index: 967883 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.1126. Min Act: -0.0000

Data Index: 1279343 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.2487. Min Act: -0.0000

Data Index: 706380 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.1648. Min Act: -0.0000

Data Index: 37465 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.1689. Min Act: -0.0000

Data Index: 1217516 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.1643. Min Act: -0.0000

Data Index: 433728 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.1161. Min Act: -0.0000

Data Index: 481828 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.1516. Min Act: -0.0000

Data Index: 930166 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.1557. Min Act: -0.0000

Data Index: 129281 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 1.7253. Min Range: -1.7253

Max Act: 1.1385. Min Act: 0.0000

Data Index: 1292649 (C4 (Web Text))

Max Activating Token Index: 558