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

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

Neuron 4058 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: 0.0549. Min Range: -0.0549

Max Act: 0.0549. Min Act: -0.0002

Data Index: 229280 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1261901 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0519. Min Act: -0.0002

Data Index: 972573 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0530. Min Act: -0.0002

Data Index: 637327 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0530. Min Act: -0.0002

Data Index: 939437 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1259128 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0472. Min Act: -0.0002

Data Index: 496326 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0484. Min Act: -0.0002

Data Index: 932936 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0404. Min Act: -0.0003

Data Index: 318871 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0468. Min Act: -0.0002

Data Index: 961126 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0439. Min Act: -0.0002

Data Index: 767287 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0410. Min Act: -0.0003

Data Index: 808377 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1623645 (Python Code)

Max Activating Token Index: 271

Text #13

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0475. Min Act: -0.0002

Data Index: 475526 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0446. Min Act: -0.0002

Data Index: 393546 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0491. Min Act: -0.0002

Data Index: 127485 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0431. Min Act: -0.0002

Data Index: 858273 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0465. Min Act: -0.0002

Data Index: 775180 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0452. Min Act: -0.0002

Data Index: 897223 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0415. Min Act: -0.0002

Data Index: 25428 (C4 (Web Text))

Max Activating Token Index: 4