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

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

Neuron 3228 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.3382. Min Act: -0.0000

Data Index: 529898 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2649. Min Act: -0.0000

Data Index: 763799 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2304. Min Act: -0.0000

Data Index: 895765 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2167. Min Act: 0.0000

Data Index: 624436 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2207. Min Act: -0.0000

Data Index: 263197 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2031. Min Act: -0.0000

Data Index: 697547 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1271215 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1255721 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2105. Min Act: -0.0000

Data Index: 1139895 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2097. Min Act: -0.0000

Data Index: 84353 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2320. Min Act: -0.0000

Data Index: 450239 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2021. Min Act: -0.0000

Data Index: 207241 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2048. Min Act: -0.0000

Data Index: 412106 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1018700 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1356078 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.1921. Min Act: 0.0000

Data Index: 543028 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.1994. Min Act: -0.0000

Data Index: 270707 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.1913. Min Act: -0.0000

Data Index: 355069 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.1971. Min Act: -0.0000

Data Index: 1030005 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.3382. Min Range: -0.3382

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1316876 (C4 (Web Text))

Max Activating Token Index: 828