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

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

Neuron 360 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.2998. Min Act: -0.0000

Data Index: 1554721 (Python Code)

Max Activating Token Index: 377

Text #1

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.3262. Min Act: -0.0000

Data Index: 1515833 (Python Code)

Max Activating Token Index: 882

Text #2

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.3079. Min Act: -0.0000

Data Index: 1453453 (Python Code)

Max Activating Token Index: 429

Text #3

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.2534. Min Act: -0.0000

Data Index: 549777 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.1573. Min Act: -0.0000

Data Index: 340161 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.0200. Min Act: -0.0000

Data Index: 1550683 (Python Code)

Max Activating Token Index: 304

Text #6

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.0835. Min Act: -0.0000

Data Index: 103781 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.0767. Min Act: -0.0000

Data Index: 697801 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.0381. Min Act: -0.0000

Data Index: 1631439 (Python Code)

Max Activating Token Index: 920

Text #9

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.0354. Min Act: -0.0000

Data Index: 1556571 (Python Code)

Max Activating Token Index: 600

Text #10

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.0187. Min Act: -0.0000

Data Index: 1452687 (Python Code)

Max Activating Token Index: 357

Text #11

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.0215. Min Act: -0.0000

Data Index: 1584512 (Python Code)

Max Activating Token Index: 340

Text #12

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.0280. Min Act: -0.0000

Data Index: 506826 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.0209. Min Act: -0.0000

Data Index: 1457889 (Python Code)

Max Activating Token Index: 931

Text #14

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.9932. Min Act: -0.0000

Data Index: 1215099 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.0173. Min Act: -0.0000

Data Index: 926512 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.9918. Min Act: -0.0000

Data Index: 140654 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.9926. Min Act: -0.0000

Data Index: 486467 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.9890. Min Act: -0.0000

Data Index: 33602 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.9528. Min Act: -0.0000

Data Index: 1449455 (Python Code)

Max Activating Token Index: 275