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

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

Neuron 2768 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.3379. Min Act: -0.0001

Data Index: 1048789 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.0680. Min Act: -0.0001

Data Index: 93885 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 1.3379. Min Range: -1.3379

Max Act: 1.0171. Min Act: -0.0001

Data Index: 1193385 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.9377. Min Act: -0.0001

Data Index: 1255173 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.9406. Min Act: -0.0001

Data Index: 351325 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.9006. Min Act: -0.0001

Data Index: 399205 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.8320. Min Act: -0.0001

Data Index: 339487 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.7557. Min Act: -0.0001

Data Index: 145500 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.7563. Min Act: -0.0001

Data Index: 739366 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.8265. Min Act: -0.0001

Data Index: 663143 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.7985. Min Act: -0.0001

Data Index: 506676 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.8267. Min Act: -0.0001

Data Index: 1186498 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.7484. Min Act: -0.0001

Data Index: 761087 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.7657. Min Act: -0.0001

Data Index: 1351612 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.7273. Min Act: -0.0001

Data Index: 1258733 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.7437. Min Act: -0.0001

Data Index: 1321918 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.7312. Min Act: -0.0001

Data Index: 1311670 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.7679. Min Act: -0.0001

Data Index: 557352 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.7370. Min Act: -0.0001

Data Index: 165525 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 1.3379. Min Range: -1.3379

Max Act: 0.7360. Min Act: -0.0001

Data Index: 170471 (C4 (Web Text))

Max Activating Token Index: 12