Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 159 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0331. Min Act: -0.0006

Data Index: 471734 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0326. Min Act: -0.0006

Data Index: 964954 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0311. Min Act: -0.0006

Data Index: 503842 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0314. Min Act: -0.0006

Data Index: 1310573 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0320. Min Act: -0.0006

Data Index: 151809 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0301. Min Act: -0.0006

Data Index: 432752 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0281. Min Act: -0.0006

Data Index: 1411 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1271463 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0301. Min Act: -0.0006

Data Index: 102364 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0285. Min Act: -0.0006

Data Index: 632332 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0289. Min Act: -0.0006

Data Index: 1180799 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0301. Min Act: -0.0006

Data Index: 1081565 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1200064 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0281. Min Act: -0.0006

Data Index: 124251 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0292. Min Act: -0.0006

Data Index: 30381 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0291. Min Act: -0.0006

Data Index: 1241229 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0272. Min Act: -0.0006

Data Index: 347492 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0283. Min Act: -0.0006

Data Index: 344704 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0276. Min Act: -0.0006

Data Index: 360776 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0271. Min Act: -0.0006

Data Index: 359617 (C4 (Web Text))

Max Activating Token Index: 727