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

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

Neuron 803 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1329. Min Range: -1.1329

Max Act: 1.1329. Min Act: -0.0000

Data Index: 1157811 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 1.1329. Min Range: -1.1329

Max Act: 1.1156. Min Act: -0.0000

Data Index: 1115841 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.9541. Min Act: -0.0000

Data Index: 284371 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.7678. Min Act: -0.0000

Data Index: 224943 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.7977. Min Act: -0.0000

Data Index: 799626 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.7427. Min Act: -0.0000

Data Index: 357049 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.8314. Min Act: -0.0000

Data Index: 1130303 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.7576. Min Act: -0.0000

Data Index: 544996 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.7524. Min Act: -0.0000

Data Index: 122275 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.7790. Min Act: -0.0000

Data Index: 627114 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1268784 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.7592. Min Act: -0.0000

Data Index: 231136 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.5839. Min Act: -0.0000

Data Index: 575535 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.6979. Min Act: -0.0000

Data Index: 49389 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1276655 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1140080 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.6596. Min Act: -0.0000

Data Index: 361940 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.5959. Min Act: -0.0000

Data Index: 458043 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.5846. Min Act: -0.0000

Data Index: 815223 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 1.1329. Min Range: -1.1329

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1047708 (C4 (Web Text))

Max Activating Token Index: 332