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

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

Neuron 4791 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0543. Min Act: -0.0002

Data Index: 353077 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0489. Min Act: -0.0002

Data Index: 727275 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0482. Min Act: -0.0002

Data Index: 397720 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0526. Min Act: -0.0002

Data Index: 567780 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0460. Min Act: -0.0002

Data Index: 519776 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1036165 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0505. Min Act: -0.0002

Data Index: 764452 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1228025 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0469. Min Act: -0.0002

Data Index: 801431 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0448. Min Act: -0.0002

Data Index: 819061 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1138114 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0463. Min Act: -0.0002

Data Index: 886550 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0438. Min Act: -0.0002

Data Index: 852674 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0436. Min Act: -0.0002

Data Index: 71425 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0441. Min Act: -0.0002

Data Index: 314850 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0381. Min Act: -0.0002

Data Index: 6190 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0444. Min Act: -0.0002

Data Index: 428345 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1303144 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1080884 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0413. Min Act: -0.0002

Data Index: 892178 (C4 (Web Text))

Max Activating Token Index: 722