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

Dataset: The Pile

Neuron 1986 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8876. Min Act: -0.0000

Data Index: 152821 (The Pile)

Max Activating Token Index: 112

Text #1

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.5062. Min Act: 0.0000

Data Index: 814319 (The Pile)

Max Activating Token Index: 193

Text #2

Max Range: 3.0148. Min Range: -3.0148

Max Act: 3.0148. Min Act: -0.0000

Data Index: 1903744 (The Pile)

Max Activating Token Index: 974

Text #3

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.5653. Min Act: -0.0000

Data Index: 142329 (The Pile)

Max Activating Token Index: 997

Text #4

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.4929. Min Act: -0.0000

Data Index: 337658 (The Pile)

Max Activating Token Index: 893

Text #5

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.9936. Min Act: -0.0000

Data Index: 1315425 (The Pile)

Max Activating Token Index: 735

Text #6

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.0742. Min Act: -0.0000

Data Index: 1882936 (The Pile)

Max Activating Token Index: 851

Text #7

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.2164. Min Act: -0.0000

Data Index: 46410 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.5635. Min Act: -0.0000

Data Index: 1462723 (The Pile)

Max Activating Token Index: 981

Text #9

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.6115. Min Act: -0.0000

Data Index: 1793146 (The Pile)

Max Activating Token Index: 589

Text #10

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.5164. Min Act: -0.0000

Data Index: 1242715 (The Pile)

Max Activating Token Index: 670

Text #11

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.3717. Min Act: -0.0000

Data Index: 936250 (The Pile)

Max Activating Token Index: 299

Text #12

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.2802. Min Act: -0.0000

Data Index: 1334187 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.2083. Min Act: -0.0000

Data Index: 1946313 (The Pile)

Max Activating Token Index: 807

Text #14

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.1319. Min Act: -0.0000

Data Index: 934091 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 3.0148. Min Range: -3.0148

Max Act: 0.9399. Min Act: -0.0000

Data Index: 334876 (The Pile)

Max Activating Token Index: 222

Text #16

Max Range: 3.0148. Min Range: -3.0148

Max Act: 1.0358. Min Act: -0.0000

Data Index: 1372832 (The Pile)

Max Activating Token Index: 54

Text #17

Max Range: 3.0148. Min Range: -3.0148

Max Act: 0.9159. Min Act: -0.0000

Data Index: 56501 (The Pile)

Max Activating Token Index: 993

Text #18

Max Range: 3.0148. Min Range: -3.0148

Max Act: 0.8690. Min Act: -0.0000

Data Index: 645412 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 3.0148. Min Range: -3.0148

Max Act: 0.8622. Min Act: -0.0000

Data Index: 1603405 (The Pile)

Max Activating Token Index: 228