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

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

Neuron 1766 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1009129 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2853. Min Act: -0.0000

Data Index: 297545 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1319448 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2841. Min Act: -0.0000

Data Index: 950761 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1350068 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2385. Min Act: -0.0000

Data Index: 55005 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2354. Min Act: -0.0000

Data Index: 499672 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2418. Min Act: -0.0000

Data Index: 38483 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2480. Min Act: -0.0000

Data Index: 77596 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2345. Min Act: -0.0000

Data Index: 541687 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2350. Min Act: -0.0000

Data Index: 892707 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2343. Min Act: -0.0000

Data Index: 44968 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1288753 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2240. Min Act: -0.0000

Data Index: 16210 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2393. Min Act: -0.0000

Data Index: 912397 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2006. Min Act: -0.0000

Data Index: 746439 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2254. Min Act: -0.0000

Data Index: 150450 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2279. Min Act: -0.0000

Data Index: 552262 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1210822 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2314. Min Act: -0.0000

Data Index: 534056 (C4 (Web Text))

Max Activating Token Index: 1010