Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 764 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.2376. Min Range: -5.2376

Max Act: 5.0541. Min Act: -0.0001

Data Index: 561832 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 5.2376. Min Range: -5.2376

Max Act: 4.9284. Min Act: -0.0001

Data Index: 1196817 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 5.2376. Min Range: -5.2376

Max Act: 5.2376. Min Act: -0.0001

Data Index: 1088761 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 5.2376. Min Range: -5.2376

Max Act: 4.8207. Min Act: -0.0001

Data Index: 1283724 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 5.2376. Min Range: -5.2376

Max Act: 4.1304. Min Act: -0.0000

Data Index: 1199888 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 5.2376. Min Range: -5.2376

Max Act: 3.9121. Min Act: -0.0000

Data Index: 1298917 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 5.2376. Min Range: -5.2376

Max Act: 4.0775. Min Act: -0.0000

Data Index: 1049517 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 5.2376. Min Range: -5.2376

Max Act: 4.0805. Min Act: -0.0000

Data Index: 1342888 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 5.2376. Min Range: -5.2376

Max Act: 3.7942. Min Act: -0.0001

Data Index: 483046 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 5.2376. Min Range: -5.2376

Max Act: 3.6019. Min Act: -0.0000

Data Index: 837146 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 5.2376. Min Range: -5.2376

Max Act: 3.7669. Min Act: -0.0000

Data Index: 1238419 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 5.2376. Min Range: -5.2376

Max Act: 3.6939. Min Act: -0.0001

Data Index: 810790 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 5.2376. Min Range: -5.2376

Max Act: 3.6833. Min Act: -0.0001

Data Index: 971767 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 5.2376. Min Range: -5.2376

Max Act: 3.6898. Min Act: -0.0001

Data Index: 42051 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 5.2376. Min Range: -5.2376

Max Act: 3.8343. Min Act: -0.0000

Data Index: 351457 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 5.2376. Min Range: -5.2376

Max Act: 3.6280. Min Act: -0.0000

Data Index: 1355453 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 5.2376. Min Range: -5.2376

Max Act: 3.7328. Min Act: -0.0001

Data Index: 684900 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 5.2376. Min Range: -5.2376

Max Act: 3.7348. Min Act: -0.0001

Data Index: 1060709 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 5.2376. Min Range: -5.2376

Max Act: 3.3852. Min Act: -0.0001

Data Index: 631324 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 5.2376. Min Range: -5.2376

Max Act: 3.6682. Min Act: -0.0000

Data Index: 341861 (C4 (Web Text))

Max Activating Token Index: 49