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

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

Neuron 4344 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: 2.0508. Min Range: -2.0508

Max Act: 2.0508. Min Act: -0.0000

Data Index: 638753 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 2.0508. Min Range: -2.0508

Max Act: 1.7273. Min Act: -0.0000

Data Index: 1120417 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 2.0508. Min Range: -2.0508

Max Act: 1.3477. Min Act: -0.0000

Data Index: 664447 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 2.0508. Min Range: -2.0508

Max Act: 1.1393. Min Act: -0.0000

Data Index: 1298598 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 2.0508. Min Range: -2.0508

Max Act: 1.1364. Min Act: -0.0000

Data Index: 1082977 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 2.0508. Min Range: -2.0508

Max Act: 1.1563. Min Act: 0.0001

Data Index: 1304116 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 2.0508. Min Range: -2.0508

Max Act: 1.1183. Min Act: 0.0001

Data Index: 391100 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 2.0508. Min Range: -2.0508

Max Act: 1.0524. Min Act: -0.0000

Data Index: 106487 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 2.0508. Min Range: -2.0508

Max Act: 1.0881. Min Act: -0.0000

Data Index: 494352 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 2.0508. Min Range: -2.0508

Max Act: 1.0354. Min Act: -0.0000

Data Index: 1255081 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 2.0508. Min Range: -2.0508

Max Act: 1.0685. Min Act: -0.0000

Data Index: 56001 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 2.0508. Min Range: -2.0508

Max Act: 0.9835. Min Act: -0.0000

Data Index: 51461 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 2.0508. Min Range: -2.0508

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1185897 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 2.0508. Min Range: -2.0508

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1123726 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 2.0508. Min Range: -2.0508

Max Act: 0.9382. Min Act: 0.0001

Data Index: 60624 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 2.0508. Min Range: -2.0508

Max Act: 0.9455. Min Act: -0.0000

Data Index: 641762 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 2.0508. Min Range: -2.0508

Max Act: 0.8812. Min Act: 0.0000

Data Index: 134852 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 2.0508. Min Range: -2.0508

Max Act: 0.9821. Min Act: -0.0000

Data Index: 859106 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 2.0508. Min Range: -2.0508

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1040900 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 2.0508. Min Range: -2.0508

Max Act: 0.8583. Min Act: -0.0000

Data Index: 618437 (C4 (Web Text))

Max Activating Token Index: 532