Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3784 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0453. Min Range: -3.0453

Max Act: 3.0453. Min Act: -0.0001

Data Index: 167041 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.8508. Min Act: -0.0001

Data Index: 183267 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.3330. Min Act: -0.0001

Data Index: 323196 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.4193. Min Act: -0.0001

Data Index: 525574 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.3504. Min Act: -0.0001

Data Index: 1340293 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.2368. Min Act: -0.0001

Data Index: 228298 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.0988. Min Act: -0.0001

Data Index: 275984 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.0334. Min Act: -0.0001

Data Index: 220139 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.3200. Min Act: -0.0001

Data Index: 394810 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.2091. Min Act: -0.0001

Data Index: 26007 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.0123. Min Act: -0.0001

Data Index: 550487 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.2230. Min Act: -0.0001

Data Index: 216959 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.1072. Min Act: -0.0001

Data Index: 571529 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 3.0453. Min Range: -3.0453

Max Act: 1.9701. Min Act: -0.0001

Data Index: 852483 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 3.0453. Min Range: -3.0453

Max Act: 1.9485. Min Act: -0.0001

Data Index: 1236981 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 3.0453. Min Range: -3.0453

Max Act: 1.9971. Min Act: -0.0001

Data Index: 573258 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.1218. Min Act: -0.0001

Data Index: 153188 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 3.0453. Min Range: -3.0453

Max Act: 1.9029. Min Act: -0.0001

Data Index: 332721 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 3.0453. Min Range: -3.0453

Max Act: 2.1006. Min Act: -0.0001

Data Index: 856908 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 3.0453. Min Range: -3.0453

Max Act: 1.9906. Min Act: -0.0001

Data Index: 755375 (C4 (Web Text))

Max Activating Token Index: 354