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

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

Neuron 1674 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: 0.0600. Min Range: -0.0600

Max Act: 0.0600. Min Act: -0.0001

Data Index: 974310 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1018672 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0395. Min Act: -0.0001

Data Index: 41498 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0356. Min Act: -0.0001

Data Index: 420384 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0317. Min Act: -0.0001

Data Index: 293428 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0346. Min Act: -0.0001

Data Index: 513479 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1332145 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0306. Min Act: -0.0001

Data Index: 233047 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0252. Min Act: -0.0001

Data Index: 354518 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0314. Min Act: -0.0001

Data Index: 191309 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0291. Min Act: -0.0001

Data Index: 293484 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0262. Min Act: -0.0001

Data Index: 897886 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0278. Min Act: -0.0001

Data Index: 695667 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0268. Min Act: -0.0001

Data Index: 207860 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0270. Min Act: -0.0001

Data Index: 1533983 (Python Code)

Max Activating Token Index: 434

Text #15

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0277. Min Act: -0.0001

Data Index: 924603 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0249. Min Act: -0.0001

Data Index: 971239 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1157700 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0259. Min Act: -0.0001

Data Index: 938982 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1065258 (C4 (Web Text))

Max Activating Token Index: 68