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

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

Neuron 3646 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: 0.3972. Min Range: -0.3972

Max Act: 0.3972. Min Act: -0.0000

Data Index: 898991 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.3166. Min Act: -0.0000

Data Index: 623699 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2892. Min Act: -0.0000

Data Index: 180331 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2784. Min Act: -0.0000

Data Index: 54233 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2637. Min Act: -0.0000

Data Index: 1278518 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2890. Min Act: -0.0000

Data Index: 1273979 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1174429 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2515. Min Act: -0.0000

Data Index: 245784 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2428. Min Act: -0.0000

Data Index: 568900 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1127057 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2466. Min Act: -0.0000

Data Index: 894796 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2501. Min Act: -0.0000

Data Index: 275610 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2513. Min Act: -0.0000

Data Index: 291557 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2351. Min Act: -0.0000

Data Index: 497873 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1220976 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2408. Min Act: -0.0000

Data Index: 672069 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2480. Min Act: -0.0000

Data Index: 966579 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2297. Min Act: -0.0000

Data Index: 104155 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2366. Min Act: -0.0000

Data Index: 722317 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.3972. Min Range: -0.3972

Max Act: 0.2326. Min Act: -0.0000

Data Index: 235330 (C4 (Web Text))

Max Activating Token Index: 681