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

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

Neuron 1438 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.5396. Min Act: -0.0001

Data Index: 757220 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.4601. Min Act: -0.0001

Data Index: 205 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.5128. Min Act: -0.0001

Data Index: 464891 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.5359. Min Act: -0.0001

Data Index: 1028320 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.4886. Min Act: -0.0001

Data Index: 57550 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.4824. Min Act: -0.0001

Data Index: 1340473 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.4979. Min Act: -0.0001

Data Index: 116937 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.4652. Min Act: -0.0001

Data Index: 438834 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.4577. Min Act: -0.0001

Data Index: 198169 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.4564. Min Act: -0.0001

Data Index: 159717 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.4438. Min Act: -0.0001

Data Index: 755946 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.4779. Min Act: -0.0001

Data Index: 354483 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.4334. Min Act: -0.0001

Data Index: 89303 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.4246. Min Act: -0.0001

Data Index: 457785 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.4866. Min Act: -0.0001

Data Index: 479270 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.4035. Min Act: -0.0001

Data Index: 708084 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.4451. Min Act: -0.0001

Data Index: 436855 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.2828. Min Act: -0.0001

Data Index: 746930 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.3967. Min Act: -0.0001

Data Index: 117257 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 1.5396. Min Range: -1.5396

Max Act: 1.3590. Min Act: -0.0001

Data Index: 1276800 (C4 (Web Text))

Max Activating Token Index: 1008