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

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

Neuron 2047 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: 1.9676. Min Range: -1.9676

Max Act: 1.9676. Min Act: -0.0000

Data Index: 573713 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.7261. Min Act: -0.0000

Data Index: 386465 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.5446. Min Act: -0.0000

Data Index: 1172736 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.4478. Min Act: -0.0000

Data Index: 1263774 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.2815. Min Act: -0.0000

Data Index: 450587 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.4308. Min Act: -0.0000

Data Index: 1113836 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.2890. Min Act: -0.0000

Data Index: 429353 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.1629. Min Act: -0.0000

Data Index: 126024 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.3108. Min Act: -0.0000

Data Index: 437626 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.1456. Min Act: -0.0000

Data Index: 1348933 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.2188. Min Act: -0.0000

Data Index: 134093 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.2426. Min Act: -0.0000

Data Index: 394799 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.1922. Min Act: -0.0000

Data Index: 9605 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.1596. Min Act: -0.0000

Data Index: 62198 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.1527. Min Act: -0.0000

Data Index: 928939 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.1094. Min Act: -0.0000

Data Index: 1005373 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.1412. Min Act: -0.0000

Data Index: 136299 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.1004. Min Act: 0.0000

Data Index: 117719 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1218795 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 1.9676. Min Range: -1.9676

Max Act: 1.1327. Min Act: -0.0000

Data Index: 9516 (C4 (Web Text))

Max Activating Token Index: 390