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

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

Neuron 3695 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: 2.1442. Min Range: -2.1442

Max Act: 2.1442. Min Act: -0.0000

Data Index: 1303768 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.8307. Min Act: -0.0000

Data Index: 916597 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.6248. Min Act: -0.0000

Data Index: 1174678 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.4755. Min Act: -0.0000

Data Index: 1287979 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.5695. Min Act: -0.0000

Data Index: 979051 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.3487. Min Act: -0.0000

Data Index: 164325 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.5134. Min Act: -0.0000

Data Index: 502679 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.4759. Min Act: -0.0000

Data Index: 913122 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.3622. Min Act: -0.0000

Data Index: 848796 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.3860. Min Act: -0.0000

Data Index: 1247147 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.2625. Min Act: -0.0000

Data Index: 837090 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.2997. Min Act: -0.0000

Data Index: 1626867 (Python Code)

Max Activating Token Index: 74

Text #12

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.2553. Min Act: -0.0000

Data Index: 300228 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.2210. Min Act: -0.0000

Data Index: 1043365 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1320206 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.2961. Min Act: -0.0000

Data Index: 1514451 (Python Code)

Max Activating Token Index: 1004

Text #16

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.2466. Min Act: -0.0000

Data Index: 241639 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.2120. Min Act: -0.0000

Data Index: 144461 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.3276. Min Act: -0.0000

Data Index: 1318862 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 2.1442. Min Range: -2.1442

Max Act: 1.2282. Min Act: -0.0000

Data Index: 261851 (C4 (Web Text))

Max Activating Token Index: 806