Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 137 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.2722. Min Act: -0.0000

Data Index: 487481 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1087587 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1271726 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.2123. Min Act: -0.0000

Data Index: 798650 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.2202. Min Act: -0.0000

Data Index: 661167 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.2211. Min Act: -0.0000

Data Index: 533315 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.2144. Min Act: -0.0001

Data Index: 50433 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.2114. Min Act: -0.0001

Data Index: 579073 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1315509 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.1911. Min Act: -0.0000

Data Index: 228266 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1195393 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.1962. Min Act: -0.0000

Data Index: 247735 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.2024. Min Act: -0.0000

Data Index: 833396 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.1985. Min Act: -0.0000

Data Index: 94343 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1021113 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.1975. Min Act: -0.0001

Data Index: 672506 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.1907. Min Act: -0.0000

Data Index: 1146657 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.1973. Min Act: -0.0000

Data Index: 497364 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1106436 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.2722. Min Range: -0.2722

Max Act: 0.1951. Min Act: -0.0000

Data Index: 614188 (C4 (Web Text))

Max Activating Token Index: 344