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

Dataset: The Pile

Neuron 2330 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1344937 (The Pile)

Max Activating Token Index: 983

Text #1

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1307395 (The Pile)

Max Activating Token Index: 697

Text #2

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4846. Min Act: -0.0000

Data Index: 36379 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4920. Min Act: -0.0000

Data Index: 829414 (The Pile)

Max Activating Token Index: 748

Text #4

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4678. Min Act: -0.0000

Data Index: 736598 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4977. Min Act: -0.0000

Data Index: 997023 (The Pile)

Max Activating Token Index: 984

Text #6

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4865. Min Act: -0.0000

Data Index: 879468 (The Pile)

Max Activating Token Index: 994

Text #7

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4662. Min Act: -0.0000

Data Index: 52524 (The Pile)

Max Activating Token Index: 920

Text #8

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1835622 (The Pile)

Max Activating Token Index: 187

Text #9

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4406. Min Act: -0.0000

Data Index: 14228 (The Pile)

Max Activating Token Index: 707

Text #10

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1210843 (The Pile)

Max Activating Token Index: 674

Text #11

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4648. Min Act: -0.0000

Data Index: 91865 (The Pile)

Max Activating Token Index: 840

Text #12

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1501994 (The Pile)

Max Activating Token Index: 965

Text #13

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4631. Min Act: -0.0000

Data Index: 114037 (The Pile)

Max Activating Token Index: 865

Text #14

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4701. Min Act: -0.0000

Data Index: 646515 (The Pile)

Max Activating Token Index: 994

Text #15

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1603438 (The Pile)

Max Activating Token Index: 183

Text #16

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4275. Min Act: -0.0000

Data Index: 1437481 (The Pile)

Max Activating Token Index: 498

Text #17

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1758259 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4224. Min Act: -0.0000

Data Index: 552048 (The Pile)

Max Activating Token Index: 844

Text #19

Max Range: 0.6223. Min Range: -0.6223

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1686849 (The Pile)

Max Activating Token Index: 737