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

Dataset: The Pile

Neuron 3204 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.5373. Min Act: -0.0001

Data Index: 463741 (The Pile)

Max Activating Token Index: 321

Text #1

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.1992. Min Act: -0.0000

Data Index: 1491174 (The Pile)

Max Activating Token Index: 831

Text #2

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.4717. Min Act: -0.0000

Data Index: 916504 (The Pile)

Max Activating Token Index: 630

Text #3

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2941. Min Act: -0.0000

Data Index: 688299 (The Pile)

Max Activating Token Index: 475

Text #4

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2200. Min Act: -0.0000

Data Index: 1805170 (The Pile)

Max Activating Token Index: 352

Text #5

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.1287. Min Act: -0.0000

Data Index: 15530 (The Pile)

Max Activating Token Index: 745

Text #6

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2620. Min Act: -0.0000

Data Index: 692034 (The Pile)

Max Activating Token Index: 230

Text #7

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.1735. Min Act: -0.0000

Data Index: 5140 (The Pile)

Max Activating Token Index: 301

Text #8

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.1255. Min Act: -0.0000

Data Index: 275230 (The Pile)

Max Activating Token Index: 724

Text #9

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2588. Min Act: -0.0000

Data Index: 456991 (The Pile)

Max Activating Token Index: 321

Text #10

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2507. Min Act: -0.0000

Data Index: 1670320 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.1893. Min Act: -0.0000

Data Index: 1962990 (The Pile)

Max Activating Token Index: 306

Text #12

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.1067. Min Act: -0.0000

Data Index: 584693 (The Pile)

Max Activating Token Index: 404

Text #13

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.0584. Min Act: -0.0001

Data Index: 1946634 (The Pile)

Max Activating Token Index: 883

Text #14

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2196. Min Act: -0.0000

Data Index: 1446622 (The Pile)

Max Activating Token Index: 119

Text #15

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.0579. Min Act: -0.0000

Data Index: 1062345 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1486805 (The Pile)

Max Activating Token Index: 688

Text #17

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.2384. Min Act: -0.0000

Data Index: 421140 (The Pile)

Max Activating Token Index: 989

Text #18

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.0373. Min Act: -0.0000

Data Index: 1271404 (The Pile)

Max Activating Token Index: 942

Text #19

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.1533. Min Act: -0.0000

Data Index: 960539 (The Pile)

Max Activating Token Index: 53