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

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

Neuron 4025 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1068973 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.7954. Min Act: -0.0000

Data Index: 1323871 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1631483 (Python Code)

Max Activating Token Index: 164

Text #3

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.7538. Min Act: -0.0000

Data Index: 390729 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.7534. Min Act: -0.0000

Data Index: 990842 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.6991. Min Act: -0.0000

Data Index: 1371151 (Python Code)

Max Activating Token Index: 601

Text #6

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.7079. Min Act: -0.0000

Data Index: 1631954 (Python Code)

Max Activating Token Index: 528

Text #7

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1499814 (Python Code)

Max Activating Token Index: 830

Text #8

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.6712. Min Act: -0.0000

Data Index: 633229 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1417800 (Python Code)

Max Activating Token Index: 259

Text #10

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1376009 (Python Code)

Max Activating Token Index: 480

Text #11

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1629340 (Python Code)

Max Activating Token Index: 271

Text #12

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.6474. Min Act: -0.0000

Data Index: 191092 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.6903. Min Act: -0.0000

Data Index: 824687 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.6263. Min Act: 0.0000

Data Index: 855113 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1369160 (Python Code)

Max Activating Token Index: 930

Text #16

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1651259 (Python Code)

Max Activating Token Index: 534

Text #17

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1381661 (Python Code)

Max Activating Token Index: 461

Text #18

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1495500 (Python Code)

Max Activating Token Index: 222

Text #19

Max Range: 0.9114. Min Range: -0.9114

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1415172 (Python Code)

Max Activating Token Index: 274