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

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

Neuron 94 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8898. Min Act: -0.0003

Data Index: 1175578 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8439. Min Act: -0.0002

Data Index: 899285 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8640. Min Act: -0.0002

Data Index: 212235 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8446. Min Act: -0.0002

Data Index: 954304 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8452. Min Act: -0.0002

Data Index: 1355053 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8402. Min Act: -0.0002

Data Index: 1242342 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8333. Min Act: -0.0002

Data Index: 860415 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8372. Min Act: -0.0002

Data Index: 801296 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8318. Min Act: -0.0002

Data Index: 339392 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8389. Min Act: -0.0003

Data Index: 746478 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8240. Min Act: -0.0002

Data Index: 289728 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8201. Min Act: -0.0002

Data Index: 956446 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8176. Min Act: -0.0002

Data Index: 285261 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.7984. Min Act: -0.0002

Data Index: 1238134 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8134. Min Act: -0.0002

Data Index: 693863 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.7968. Min Act: -0.0003

Data Index: 1057193 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8038. Min Act: -0.0002

Data Index: 221744 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.7889. Min Act: -0.0002

Data Index: 56581 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.7863. Min Act: -0.0003

Data Index: 365751 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.7800. Min Act: -0.0002

Data Index: 440451 (C4 (Web Text))

Max Activating Token Index: 584