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

Dataset: The Pile

Neuron 382 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: 1.3570. Min Range: -1.3570

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1962172 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.3011. Min Act: -0.0000

Data Index: 1553211 (The Pile)

Max Activating Token Index: 962

Text #2

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1499. Min Act: -0.0000

Data Index: 704403 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.3371. Min Act: -0.0000

Data Index: 1552295 (The Pile)

Max Activating Token Index: 480

Text #4

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.3150. Min Act: -0.0000

Data Index: 304571 (The Pile)

Max Activating Token Index: 231

Text #5

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1422758 (The Pile)

Max Activating Token Index: 62

Text #6

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.2029. Min Act: -0.0000

Data Index: 1475371 (The Pile)

Max Activating Token Index: 470

Text #7

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0929. Min Act: -0.0000

Data Index: 471777 (The Pile)

Max Activating Token Index: 688

Text #8

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.2640. Min Act: -0.0000

Data Index: 764163 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.2002. Min Act: -0.0000

Data Index: 135429 (The Pile)

Max Activating Token Index: 128

Text #10

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1651. Min Act: -0.0000

Data Index: 495885 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0482. Min Act: -0.0000

Data Index: 1907572 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1629. Min Act: -0.0000

Data Index: 1948501 (The Pile)

Max Activating Token Index: 118

Text #13

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0240. Min Act: -0.0000

Data Index: 851978 (The Pile)

Max Activating Token Index: 243

Text #14

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0553. Min Act: -0.0000

Data Index: 1568361 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1719. Min Act: -0.0000

Data Index: 626328 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9304. Min Act: -0.0000

Data Index: 816183 (The Pile)

Max Activating Token Index: 779

Text #17

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1385. Min Act: -0.0000

Data Index: 589674 (The Pile)

Max Activating Token Index: 51

Text #18

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0259. Min Act: -0.0000

Data Index: 1790834 (The Pile)

Max Activating Token Index: 210

Text #19

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0659. Min Act: -0.0000

Data Index: 680802 (The Pile)

Max Activating Token Index: 289