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

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

Neuron 220 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0001

Data Index: 408700 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0331. Min Act: -0.0001

Data Index: 165600 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0311. Min Act: -0.0001

Data Index: 375627 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0327. Min Act: -0.0001

Data Index: 202385 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0287. Min Act: -0.0001

Data Index: 375634 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0287. Min Act: -0.0001

Data Index: 305805 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0293. Min Act: -0.0001

Data Index: 670935 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0300. Min Act: -0.0001

Data Index: 867797 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0272. Min Act: -0.0001

Data Index: 661064 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1243427 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1342191 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0263. Min Act: -0.0001

Data Index: 329450 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0272. Min Act: -0.0001

Data Index: 125114 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0253. Min Act: -0.0001

Data Index: 79438 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0260. Min Act: -0.0001

Data Index: 8204 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0253. Min Act: -0.0001

Data Index: 348597 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1185476 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1357543 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0260. Min Act: -0.0001

Data Index: 50920 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0249. Min Act: -0.0001

Data Index: 1178760 (C4 (Web Text))

Max Activating Token Index: 196