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

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

Neuron 3347 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.8228. Min Act: -0.0001

Data Index: 90901 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.7666. Min Act: -0.0001

Data Index: 457277 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.7223. Min Act: -0.0001

Data Index: 609114 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.7322. Min Act: -0.0001

Data Index: 260176 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.7208. Min Act: -0.0001

Data Index: 342665 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.6927. Min Act: -0.0001

Data Index: 432613 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.6675. Min Act: -0.0001

Data Index: 760869 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.6675. Min Act: -0.0001

Data Index: 1197348 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.6367. Min Act: -0.0001

Data Index: 1347951 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.6571. Min Act: -0.0001

Data Index: 1176701 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.6348. Min Act: -0.0001

Data Index: 59272 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.6723. Min Act: -0.0001

Data Index: 989845 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.6456. Min Act: -0.0001

Data Index: 1139846 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.6433. Min Act: -0.0001

Data Index: 110363 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.5862. Min Act: -0.0001

Data Index: 607718 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.6266. Min Act: -0.0001

Data Index: 624165 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.6050. Min Act: -0.0001

Data Index: 1184682 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.5977. Min Act: -0.0001

Data Index: 713070 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.5959. Min Act: -0.0001

Data Index: 1404317 (Python Code)

Max Activating Token Index: 214

Text #19

Max Range: 0.8228. Min Range: -0.8228

Max Act: 0.5954. Min Act: -0.0001

Data Index: 562819 (C4 (Web Text))

Max Activating Token Index: 101