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

Dataset: The Pile

Neuron 2814 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: 0.8968. Min Range: -0.8968

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1615176 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1168463 (The Pile)

Max Activating Token Index: 295

Text #2

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1663170 (The Pile)

Max Activating Token Index: 181

Text #3

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1000378 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7905. Min Act: -0.0000

Data Index: 235498 (The Pile)

Max Activating Token Index: 416

Text #5

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1052807 (The Pile)

Max Activating Token Index: 294

Text #6

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.8968. Min Act: -0.0000

Data Index: 3942 (The Pile)

Max Activating Token Index: 782

Text #7

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7320. Min Act: -0.0000

Data Index: 127172 (The Pile)

Max Activating Token Index: 246

Text #8

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7779. Min Act: -0.0000

Data Index: 179694 (The Pile)

Max Activating Token Index: 19

Text #9

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1526375 (The Pile)

Max Activating Token Index: 823

Text #10

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6683. Min Act: -0.0000

Data Index: 632417 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7556. Min Act: -0.0000

Data Index: 497421 (The Pile)

Max Activating Token Index: 964

Text #12

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7138. Min Act: -0.0000

Data Index: 1637228 (The Pile)

Max Activating Token Index: 973

Text #13

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1060286 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1643665 (The Pile)

Max Activating Token Index: 426

Text #15

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1524059 (The Pile)

Max Activating Token Index: 58

Text #16

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6924. Min Act: -0.0000

Data Index: 1885048 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1069532 (The Pile)

Max Activating Token Index: 613

Text #18

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1715110 (The Pile)

Max Activating Token Index: 805

Text #19

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1959857 (The Pile)

Max Activating Token Index: 614