Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4084 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1262990 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1799. Min Act: -0.0000

Data Index: 49416 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1606. Min Act: -0.0001

Data Index: 1116226 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1672. Min Act: -0.0000

Data Index: 1276291 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1496. Min Act: -0.0000

Data Index: 192481 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1291. Min Act: -0.0000

Data Index: 91099 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1197101 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1658. Min Act: -0.0000

Data Index: 461012 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1365. Min Act: -0.0001

Data Index: 163669 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1321. Min Act: -0.0001

Data Index: 1282000 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1574. Min Act: -0.0001

Data Index: 1339190 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1659. Min Act: -0.0001

Data Index: 144270 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1553. Min Act: -0.0000

Data Index: 367555 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1547. Min Act: -0.0000

Data Index: 596495 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1560. Min Act: -0.0000

Data Index: 803540 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1121624 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1204. Min Act: -0.0000

Data Index: 914552 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1441. Min Act: -0.0001

Data Index: 346534 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1016226 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1169663 (C4 (Web Text))

Max Activating Token Index: 935