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

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

Neuron 3703 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4789. Min Act: -0.0001

Data Index: 851335 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.0345. Min Act: -0.0001

Data Index: 967873 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.8445. Min Act: -0.0001

Data Index: 231155 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.8720. Min Act: -0.0001

Data Index: 1269877 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.9121. Min Act: -0.0001

Data Index: 1352089 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.9078. Min Act: -0.0001

Data Index: 226818 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.8542. Min Act: -0.0001

Data Index: 1264612 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.8548. Min Act: -0.0001

Data Index: 1229203 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.8682. Min Act: -0.0001

Data Index: 1351429 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.8195. Min Act: -0.0001

Data Index: 129942 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.8958. Min Act: -0.0001

Data Index: 879730 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.7989. Min Act: -0.0001

Data Index: 1353559 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.8397. Min Act: -0.0001

Data Index: 781513 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.8506. Min Act: -0.0001

Data Index: 873064 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.6718. Min Act: -0.0001

Data Index: 996427 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.8258. Min Act: -0.0001

Data Index: 286623 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.8455. Min Act: -0.0001

Data Index: 427345 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.8188. Min Act: -0.0001

Data Index: 976966 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.8067. Min Act: -0.0001

Data Index: 623818 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 1.4789. Min Range: -1.4789

Max Act: 0.8459. Min Act: -0.0001

Data Index: 250281 (C4 (Web Text))

Max Activating Token Index: 758