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

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

Neuron 3060 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: 1.4532. Min Range: -1.4532

Max Act: 1.4532. Min Act: -0.0001

Data Index: 935038 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.3672. Min Act: -0.0000

Data Index: 1235834 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.4104. Min Act: -0.0001

Data Index: 78293 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2486. Min Act: -0.0000

Data Index: 989182 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2356. Min Act: -0.0001

Data Index: 988122 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1797. Min Act: -0.0000

Data Index: 685532 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1520. Min Act: -0.0000

Data Index: 1288617 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1517. Min Act: -0.0000

Data Index: 718527 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.2132. Min Act: -0.0000

Data Index: 657966 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1355. Min Act: -0.0000

Data Index: 869465 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1413. Min Act: -0.0000

Data Index: 464324 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1284. Min Act: -0.0000

Data Index: 590789 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.0874. Min Act: -0.0000

Data Index: 539929 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.0887. Min Act: -0.0001

Data Index: 246131 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1144. Min Act: -0.0000

Data Index: 1092660 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.0660. Min Act: -0.0000

Data Index: 144311 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1312. Min Act: -0.0000

Data Index: 511631 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1297102 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1014. Min Act: -0.0001

Data Index: 96109 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 1.4532. Min Range: -1.4532

Max Act: 1.1315. Min Act: -0.0000

Data Index: 81776 (C4 (Web Text))

Max Activating Token Index: 242