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

Dataset: The Pile

Neuron 600 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: 1.5346. Min Range: -1.5346

Max Act: 1.5346. Min Act: -0.0000

Data Index: 652638 (The Pile)

Max Activating Token Index: 891

Text #1

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.4660. Min Act: -0.0000

Data Index: 694191 (The Pile)

Max Activating Token Index: 478

Text #2

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.3482. Min Act: -0.0000

Data Index: 1485906 (The Pile)

Max Activating Token Index: 317

Text #3

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.2492. Min Act: -0.0000

Data Index: 1819577 (The Pile)

Max Activating Token Index: 757

Text #4

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.2217. Min Act: -0.0000

Data Index: 1682566 (The Pile)

Max Activating Token Index: 153

Text #5

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.2245. Min Act: -0.0000

Data Index: 690743 (The Pile)

Max Activating Token Index: 572

Text #6

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.1285. Min Act: -0.0000

Data Index: 287781 (The Pile)

Max Activating Token Index: 464

Text #7

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.2351. Min Act: -0.0000

Data Index: 508401 (The Pile)

Max Activating Token Index: 514

Text #8

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.1499. Min Act: -0.0000

Data Index: 1281522 (The Pile)

Max Activating Token Index: 316

Text #9

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.0220. Min Act: -0.0000

Data Index: 1419562 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.1696. Min Act: -0.0000

Data Index: 1556144 (The Pile)

Max Activating Token Index: 348

Text #11

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.1523. Min Act: -0.0000

Data Index: 971352 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1091478 (The Pile)

Max Activating Token Index: 453

Text #13

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.1203. Min Act: -0.0000

Data Index: 974018 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.0705. Min Act: -0.0000

Data Index: 472514 (The Pile)

Max Activating Token Index: 169

Text #15

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.9616. Min Act: -0.0000

Data Index: 226747 (The Pile)

Max Activating Token Index: 251

Text #16

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1389421 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.0009. Min Act: -0.0000

Data Index: 709948 (The Pile)

Max Activating Token Index: 623

Text #18

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.8402. Min Act: -0.0000

Data Index: 359905 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.8824. Min Act: -0.0000

Data Index: 122441 (The Pile)

Max Activating Token Index: 840