Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3233 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0001

Data Index: 631402 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0147. Min Act: -0.0000

Data Index: 728257 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0154. Min Act: -0.0001

Data Index: 399588 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0148. Min Act: -0.0001

Data Index: 1251556 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0144. Min Act: -0.0001

Data Index: 303463 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0144. Min Act: -0.0000

Data Index: 1145716 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0145. Min Act: -0.0001

Data Index: 561802 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0128. Min Act: -0.0000

Data Index: 1538317 (Python Code)

Max Activating Token Index: 825

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0127. Min Act: -0.0000

Data Index: 837664 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0122. Min Act: -0.0000

Data Index: 1656474 (Python Code)

Max Activating Token Index: 609

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0127. Min Act: -0.0001

Data Index: 1601844 (Python Code)

Max Activating Token Index: 794

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0125. Min Act: -0.0000

Data Index: 237233 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0124. Min Act: -0.0000

Data Index: 1614431 (Python Code)

Max Activating Token Index: 584

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0123. Min Act: -0.0001

Data Index: 1276947 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0123. Min Act: -0.0000

Data Index: 1229926 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0118. Min Act: -0.0000

Data Index: 515362 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0118. Min Act: -0.0001

Data Index: 8155 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0122. Min Act: -0.0000

Data Index: 1304658 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0123. Min Act: -0.0000

Data Index: 1418818 (Python Code)

Max Activating Token Index: 614

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0121. Min Act: -0.0000

Data Index: 1147117 (C4 (Web Text))

Max Activating Token Index: 403