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

Dataset: The Pile

Neuron 3667 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: 0.4788. Min Range: -0.4788

Max Act: 0.4279. Min Act: -0.0000

Data Index: 766769 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1034524 (The Pile)

Max Activating Token Index: 458

Text #2

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1533788 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4006. Min Act: -0.0000

Data Index: 487108 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3898. Min Act: -0.0000

Data Index: 338763 (The Pile)

Max Activating Token Index: 526

Text #5

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1744101 (The Pile)

Max Activating Token Index: 633

Text #6

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3511. Min Act: -0.0000

Data Index: 265958 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1170341 (The Pile)

Max Activating Token Index: 247

Text #8

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3462. Min Act: -0.0000

Data Index: 335942 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3379. Min Act: -0.0000

Data Index: 857887 (The Pile)

Max Activating Token Index: 384

Text #10

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3169. Min Act: -0.0000

Data Index: 968479 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1344401 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3248. Min Act: -0.0000

Data Index: 352226 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3272. Min Act: -0.0000

Data Index: 1224043 (The Pile)

Max Activating Token Index: 933

Text #14

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3275. Min Act: -0.0000

Data Index: 80374 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1566141 (The Pile)

Max Activating Token Index: 586

Text #16

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1029244 (The Pile)

Max Activating Token Index: 911

Text #17

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1098198 (The Pile)

Max Activating Token Index: 601

Text #18

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3072. Min Act: -0.0000

Data Index: 665677 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1528017 (The Pile)

Max Activating Token Index: 661