Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2196 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0555. Min Act: -0.0002

Data Index: 900030 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0558. Min Act: -0.0002

Data Index: 993264 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1125457 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1189073 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0554. Min Act: -0.0002

Data Index: 889775 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0542. Min Act: -0.0001

Data Index: 1112892 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0538. Min Act: -0.0001

Data Index: 225367 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1617803 (Python Code)

Max Activating Token Index: 85

Text #8

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1143330 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0492. Min Act: -0.0001

Data Index: 588515 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1260235 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1313613 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0465. Min Act: -0.0002

Data Index: 988867 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0484. Min Act: -0.0001

Data Index: 909565 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0485. Min Act: -0.0001

Data Index: 405871 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0492. Min Act: -0.0001

Data Index: 744408 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0471. Min Act: -0.0001

Data Index: 1560556 (Python Code)

Max Activating Token Index: 346

Text #17

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0468. Min Act: -0.0002

Data Index: 649473 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0471. Min Act: -0.0001

Data Index: 938299 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0426. Min Act: -0.0001

Data Index: 1197821 (C4 (Web Text))

Max Activating Token Index: 121