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

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

Neuron 5744 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5268. Min Range: -2.5268

Max Act: 2.5268. Min Act: -0.0000

Data Index: 828809 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 2.5268. Min Range: -2.5268

Max Act: 2.0059. Min Act: -0.0000

Data Index: 174595 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 2.5268. Min Range: -2.5268

Max Act: 2.0901. Min Act: -0.0000

Data Index: 1022601 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.6465. Min Act: -0.0000

Data Index: 676271 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.7900. Min Act: -0.0000

Data Index: 647034 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.5458. Min Act: -0.0000

Data Index: 383347 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.5187. Min Act: -0.0000

Data Index: 535477 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.4714. Min Act: -0.0000

Data Index: 851918 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.4415. Min Act: -0.0000

Data Index: 941157 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.4171. Min Act: -0.0000

Data Index: 924537 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.3246. Min Act: -0.0000

Data Index: 473015 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.2135. Min Act: -0.0000

Data Index: 1165795 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.2900. Min Act: -0.0000

Data Index: 662896 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.2734. Min Act: -0.0000

Data Index: 1068533 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.1883. Min Act: -0.0000

Data Index: 1341903 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.2373. Min Act: -0.0000

Data Index: 3897 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.2021. Min Act: -0.0000

Data Index: 1331591 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.2288. Min Act: -0.0000

Data Index: 303128 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.2891. Min Act: -0.0000

Data Index: 357420 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 2.5268. Min Range: -2.5268

Max Act: 1.2622. Min Act: -0.0000

Data Index: 1341670 (C4 (Web Text))

Max Activating Token Index: 1002