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

Dataset: The Pile

Neuron 2982 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: 0.4776. Min Range: -0.4776

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1655797 (The Pile)

Max Activating Token Index: 531

Text #1

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1343850 (The Pile)

Max Activating Token Index: 385

Text #2

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1457998 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3755. Min Act: -0.0000

Data Index: 672308 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1529393 (The Pile)

Max Activating Token Index: 893

Text #5

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1201486 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1990856 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3297. Min Act: -0.0000

Data Index: 350423 (The Pile)

Max Activating Token Index: 975

Text #8

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3435. Min Act: -0.0000

Data Index: 835065 (The Pile)

Max Activating Token Index: 216

Text #9

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3289. Min Act: -0.0000

Data Index: 237816 (The Pile)

Max Activating Token Index: 884

Text #10

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3453. Min Act: -0.0000

Data Index: 1289242 (The Pile)

Max Activating Token Index: 665

Text #11

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1407984 (The Pile)

Max Activating Token Index: 231

Text #12

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3232. Min Act: -0.0000

Data Index: 602745 (The Pile)

Max Activating Token Index: 970

Text #13

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1316601 (The Pile)

Max Activating Token Index: 131

Text #14

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1621370 (The Pile)

Max Activating Token Index: 771

Text #15

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1065154 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3235. Min Act: -0.0000

Data Index: 567359 (The Pile)

Max Activating Token Index: 645

Text #17

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3071. Min Act: -0.0000

Data Index: 1653453 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1607424 (The Pile)

Max Activating Token Index: 239

Text #19

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3060. Min Act: -0.0000

Data Index: 15223 (The Pile)

Max Activating Token Index: 711