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

Dataset: The Pile

Neuron 2429 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0198. Min Range: -1.0198

Max Act: 1.0198. Min Act: -0.0000

Data Index: 839622 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.9958. Min Act: -0.0000

Data Index: 909815 (The Pile)

Max Activating Token Index: 989

Text #2

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.9641. Min Act: -0.0000

Data Index: 1695812 (The Pile)

Max Activating Token Index: 466

Text #3

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.9736. Min Act: -0.0000

Data Index: 629833 (The Pile)

Max Activating Token Index: 753

Text #4

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.9803. Min Act: -0.0000

Data Index: 753481 (The Pile)

Max Activating Token Index: 972

Text #5

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.9171. Min Act: -0.0000

Data Index: 676362 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8927. Min Act: -0.0000

Data Index: 1000676 (The Pile)

Max Activating Token Index: 242

Text #7

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1094354 (The Pile)

Max Activating Token Index: 625

Text #8

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1674958 (The Pile)

Max Activating Token Index: 935

Text #9

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8654. Min Act: -0.0000

Data Index: 498281 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1036774 (The Pile)

Max Activating Token Index: 339

Text #11

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1707608 (The Pile)

Max Activating Token Index: 609

Text #12

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1550992 (The Pile)

Max Activating Token Index: 965

Text #13

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8479. Min Act: -0.0000

Data Index: 547131 (The Pile)

Max Activating Token Index: 458

Text #14

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8814. Min Act: -0.0000

Data Index: 613369 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1867568 (The Pile)

Max Activating Token Index: 240

Text #16

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8239. Min Act: -0.0000

Data Index: 576350 (The Pile)

Max Activating Token Index: 819

Text #17

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1963391 (The Pile)

Max Activating Token Index: 77

Text #18

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.7916. Min Act: -0.0000

Data Index: 499105 (The Pile)

Max Activating Token Index: 191

Text #19

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8351. Min Act: -0.0000

Data Index: 920220 (The Pile)

Max Activating Token Index: 724