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

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

Neuron 4579 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: 1.2337. Min Range: -1.2337

Max Act: 1.2337. Min Act: -0.0000

Data Index: 513808 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 1.2337. Min Range: -1.2337

Max Act: 1.2273. Min Act: -0.0000

Data Index: 1182337 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 1.2337. Min Range: -1.2337

Max Act: 1.2236. Min Act: -0.0000

Data Index: 242229 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 1.2337. Min Range: -1.2337

Max Act: 1.1762. Min Act: -0.0000

Data Index: 1009559 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.2337. Min Range: -1.2337

Max Act: 1.1901. Min Act: -0.0000

Data Index: 1219607 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.2337. Min Range: -1.2337

Max Act: 1.0759. Min Act: -0.0000

Data Index: 1305691 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 1.2337. Min Range: -1.2337

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1308820 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 1.2337. Min Range: -1.2337

Max Act: 1.0758. Min Act: -0.0000

Data Index: 901356 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 1.2337. Min Range: -1.2337

Max Act: 1.0274. Min Act: -0.0000

Data Index: 151977 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 1.2337. Min Range: -1.2337

Max Act: 1.0944. Min Act: -0.0000

Data Index: 757600 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 1.2337. Min Range: -1.2337

Max Act: 0.9330. Min Act: -0.0000

Data Index: 1347808 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 1.2337. Min Range: -1.2337

Max Act: 0.9609. Min Act: -0.0000

Data Index: 293115 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 1.2337. Min Range: -1.2337

Max Act: 0.9043. Min Act: -0.0000

Data Index: 630925 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 1.2337. Min Range: -1.2337

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1041570 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 1.2337. Min Range: -1.2337

Max Act: 0.8340. Min Act: -0.0000

Data Index: 71423 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 1.2337. Min Range: -1.2337

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1552544 (Python Code)

Max Activating Token Index: 759

Text #16

Max Range: 1.2337. Min Range: -1.2337

Max Act: 0.8338. Min Act: -0.0000

Data Index: 949215 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 1.2337. Min Range: -1.2337

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1477253 (Python Code)

Max Activating Token Index: 808

Text #18

Max Range: 1.2337. Min Range: -1.2337

Max Act: 0.7459. Min Act: -0.0000

Data Index: 641945 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 1.2337. Min Range: -1.2337

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1201620 (C4 (Web Text))

Max Activating Token Index: 211