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

Dataset: The Pile

Neuron 1607 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9338. Min Act: -0.0000

Data Index: 1668683 (The Pile)

Max Activating Token Index: 150

Text #1

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9310. Min Act: -0.0000

Data Index: 1550248 (The Pile)

Max Activating Token Index: 264

Text #2

Max Range: 1.0151. Min Range: -1.0151

Max Act: 1.0151. Min Act: -0.0000

Data Index: 536488 (The Pile)

Max Activating Token Index: 145

Text #3

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8773. Min Act: -0.0000

Data Index: 921573 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1142974 (The Pile)

Max Activating Token Index: 823

Text #5

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8421. Min Act: -0.0000

Data Index: 86541 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9282. Min Act: -0.0000

Data Index: 230718 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8114. Min Act: -0.0000

Data Index: 1816537 (The Pile)

Max Activating Token Index: 150

Text #8

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8240. Min Act: -0.0000

Data Index: 779315 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8041. Min Act: -0.0000

Data Index: 662927 (The Pile)

Max Activating Token Index: 527

Text #10

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1935426 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7094. Min Act: -0.0000

Data Index: 633509 (The Pile)

Max Activating Token Index: 175

Text #12

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7408. Min Act: -0.0000

Data Index: 411012 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7051. Min Act: -0.0000

Data Index: 8090 (The Pile)

Max Activating Token Index: 975

Text #14

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1063323 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7282. Min Act: -0.0000

Data Index: 414562 (The Pile)

Max Activating Token Index: 320

Text #16

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1383642 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6084. Min Act: -0.0000

Data Index: 789710 (The Pile)

Max Activating Token Index: 978

Text #18

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6584. Min Act: -0.0000

Data Index: 782205 (The Pile)

Max Activating Token Index: 412

Text #19

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7126. Min Act: -0.0000

Data Index: 361711 (The Pile)

Max Activating Token Index: 317