Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 678 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.3425. Min Act: -0.0000

Data Index: 813613 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2913. Min Act: -0.0000

Data Index: 513750 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2502. Min Act: -0.0000

Data Index: 411025 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1150910 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1675. Min Act: -0.0000

Data Index: 1511538 (Python Code)

Max Activating Token Index: 658

Text #5

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1094673 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1610. Min Act: -0.0000

Data Index: 509118 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1593. Min Act: -0.0000

Data Index: 141745 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1091902 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1041362 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1643. Min Act: -0.0000

Data Index: 928454 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1416. Min Act: -0.0000

Data Index: 495751 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1662. Min Act: -0.0000

Data Index: 531866 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1387. Min Act: -0.0000

Data Index: 268300 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1418. Min Act: -0.0000

Data Index: 604046 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1393. Min Act: -0.0000

Data Index: 1251667 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1316. Min Act: -0.0000

Data Index: 682647 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1298. Min Act: -0.0000

Data Index: 1654435 (Python Code)

Max Activating Token Index: 368

Text #18

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1298. Min Act: -0.0000

Data Index: 1033813 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1343. Min Act: -0.0000

Data Index: 617958 (C4 (Web Text))

Max Activating Token Index: 86