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

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

Neuron 1474 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.4248. Min Act: -0.0000

Data Index: 1157082 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.2402. Min Act: -0.0000

Data Index: 875361 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.2698. Min Act: -0.0000

Data Index: 1292444 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.2008. Min Act: -0.0000

Data Index: 963380 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.1566. Min Act: -0.0000

Data Index: 417795 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.1826. Min Act: -0.0000

Data Index: 453450 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.1194. Min Act: -0.0000

Data Index: 147216 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.1191. Min Act: -0.0000

Data Index: 813459 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.0881. Min Act: -0.0000

Data Index: 1336275 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.1199. Min Act: -0.0000

Data Index: 115201 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.1165. Min Act: -0.0000

Data Index: 176670 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1239417 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.0857. Min Act: -0.0000

Data Index: 1307955 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.0942. Min Act: -0.0000

Data Index: 56609 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.0823. Min Act: -0.0000

Data Index: 459510 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 1.4248. Min Range: -1.4248

Max Act: 0.9812. Min Act: -0.0000

Data Index: 524874 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.0378. Min Act: -0.0000

Data Index: 792465 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.1032. Min Act: -0.0000

Data Index: 1278234 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 1.4248. Min Range: -1.4248

Max Act: 0.9422. Min Act: -0.0000

Data Index: 836468 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 1.4248. Min Range: -1.4248

Max Act: 0.9466. Min Act: -0.0000

Data Index: 181356 (C4 (Web Text))

Max Activating Token Index: 28