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

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

Neuron 1457 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1693. Min Act: -0.0001

Data Index: 741440 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1748. Min Act: -0.0001

Data Index: 407944 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1645. Min Act: -0.0001

Data Index: 1178368 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1559. Min Act: -0.0001

Data Index: 569070 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1616. Min Act: -0.0001

Data Index: 310247 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1320. Min Act: -0.0001

Data Index: 124199 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1337519 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1383. Min Act: -0.0001

Data Index: 1231989 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1520. Min Act: -0.0001

Data Index: 719096 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1248. Min Act: -0.0001

Data Index: 204857 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1445. Min Act: -0.0001

Data Index: 850561 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1373. Min Act: -0.0001

Data Index: 1322981 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1349. Min Act: -0.0001

Data Index: 30409 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1455. Min Act: -0.0001

Data Index: 535398 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1335. Min Act: -0.0001

Data Index: 1241726 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1273. Min Act: -0.0001

Data Index: 537422 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1361. Min Act: -0.0001

Data Index: 868905 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1328. Min Act: -0.0001

Data Index: 398712 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1306. Min Act: -0.0001

Data Index: 1275211 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1248. Min Act: -0.0001

Data Index: 3832 (C4 (Web Text))

Max Activating Token Index: 859