Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1355 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.9898. Min Act: -0.0000

Data Index: 553452 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.9416. Min Act: -0.0000

Data Index: 1008199 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.9233. Min Act: -0.0000

Data Index: 816409 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.7109. Min Act: -0.0000

Data Index: 1308509 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.6367. Min Act: -0.0000

Data Index: 1213962 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.9777. Min Act: -0.0000

Data Index: 52949 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.6979. Min Act: -0.0000

Data Index: 796187 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.7840. Min Act: -0.0000

Data Index: 553759 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.6105. Min Act: -0.0000

Data Index: 1323109 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.4868. Min Act: -0.0000

Data Index: 15237 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.4548. Min Act: -0.0000

Data Index: 459168 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.4365. Min Act: -0.0000

Data Index: 1222261 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.2851. Min Act: -0.0000

Data Index: 471282 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.4020. Min Act: -0.0000

Data Index: 149840 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.4917. Min Act: -0.0000

Data Index: 929075 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.4952. Min Act: -0.0000

Data Index: 1052338 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.3698. Min Act: -0.0000

Data Index: 340849 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.3450. Min Act: -0.0000

Data Index: 645415 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 2.9898. Min Range: -2.9898

Max Act: 2.2413. Min Act: -0.0000

Data Index: 1169286 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 2.9898. Min Range: -2.9898

Max Act: 1.9930. Min Act: -0.0000

Data Index: 1203378 (C4 (Web Text))

Max Activating Token Index: 651