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

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

Neuron 4342 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: 0.2510. Min Range: -0.2510

Max Act: 0.2510. Min Act: -0.0000

Data Index: 668763 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1534. Min Act: -0.0000

Data Index: 1270369 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1537. Min Act: -0.0000

Data Index: 654525 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1536. Min Act: -0.0000

Data Index: 335292 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1432. Min Act: -0.0000

Data Index: 584787 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1459. Min Act: -0.0000

Data Index: 223241 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1390. Min Act: -0.0000

Data Index: 179189 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1405. Min Act: -0.0000

Data Index: 224048 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1404. Min Act: -0.0000

Data Index: 797703 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1082606 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1276. Min Act: -0.0000

Data Index: 898163 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1471. Min Act: -0.0000

Data Index: 36756 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1330. Min Act: -0.0000

Data Index: 205649 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1466. Min Act: -0.0000

Data Index: 64944 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1302. Min Act: -0.0000

Data Index: 973306 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1286. Min Act: -0.0000

Data Index: 117125 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1367. Min Act: -0.0000

Data Index: 383430 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1356. Min Act: -0.0000

Data Index: 24759 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1290. Min Act: -0.0000

Data Index: 40044 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1202. Min Act: -0.0000

Data Index: 922910 (C4 (Web Text))

Max Activating Token Index: 608