Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1504 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0337. Min Act: -0.0001

Data Index: 1185131 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1199653 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0309. Min Act: -0.0001

Data Index: 894540 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0307. Min Act: -0.0001

Data Index: 460049 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0291. Min Act: -0.0001

Data Index: 1185384 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0287. Min Act: -0.0001

Data Index: 1360576 (Python Code)

Max Activating Token Index: 335

Text #6

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1393642 (Python Code)

Max Activating Token Index: 278

Text #7

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1630965 (Python Code)

Max Activating Token Index: 483

Text #8

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1504289 (Python Code)

Max Activating Token Index: 106

Text #9

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0284. Min Act: -0.0001

Data Index: 526244 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0269. Min Act: -0.0001

Data Index: 1499041 (Python Code)

Max Activating Token Index: 160

Text #11

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0269. Min Act: -0.0001

Data Index: 1490237 (Python Code)

Max Activating Token Index: 309

Text #12

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1524470 (Python Code)

Max Activating Token Index: 178

Text #13

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0258. Min Act: -0.0001

Data Index: 1437044 (Python Code)

Max Activating Token Index: 385

Text #14

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1488772 (Python Code)

Max Activating Token Index: 550

Text #15

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0255. Min Act: -0.0001

Data Index: 1364346 (Python Code)

Max Activating Token Index: 529

Text #16

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1547046 (Python Code)

Max Activating Token Index: 129

Text #17

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0261. Min Act: -0.0001

Data Index: 762922 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0247. Min Act: -0.0001

Data Index: 914401 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0230. Min Act: -0.0001

Data Index: 135854 (C4 (Web Text))

Max Activating Token Index: 342