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

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

Neuron 2681 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.5586. Min Act: -0.0001

Data Index: 346587 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.3005. Min Act: -0.0000

Data Index: 771555 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.2665. Min Act: -0.0000

Data Index: 408375 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.1973. Min Act: -0.0000

Data Index: 450166 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.2840. Min Act: -0.0000

Data Index: 628895 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.2484. Min Act: -0.0001

Data Index: 1126270 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.2544. Min Act: -0.0001

Data Index: 960954 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.2776. Min Act: -0.0001

Data Index: 1320523 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.0756. Min Act: -0.0001

Data Index: 1312792 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.1373. Min Act: -0.0001

Data Index: 420271 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.1259. Min Act: -0.0001

Data Index: 1311033 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.1522. Min Act: -0.0000

Data Index: 349137 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 1.5586. Min Range: -1.5586

Max Act: 0.9961. Min Act: -0.0000

Data Index: 442451 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.3604. Min Act: -0.0001

Data Index: 1466628 (Python Code)

Max Activating Token Index: 757

Text #14

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.0562. Min Act: -0.0000

Data Index: 49414 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.1063. Min Act: -0.0001

Data Index: 987637 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1197200 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1192696 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.1358. Min Act: -0.0000

Data Index: 1078743 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 1.5586. Min Range: -1.5586

Max Act: 1.0309. Min Act: -0.0000

Data Index: 981938 (C4 (Web Text))

Max Activating Token Index: 12