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

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

Neuron 2708 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.7864. Min Act: -0.0001

Data Index: 957690 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.7402. Min Act: -0.0001

Data Index: 664628 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.7761. Min Act: -0.0001

Data Index: 1177840 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.7052. Min Act: -0.0001

Data Index: 351450 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5845. Min Act: -0.0001

Data Index: 1027772 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5719. Min Act: -0.0001

Data Index: 243069 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5686. Min Act: -0.0001

Data Index: 1334912 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5455. Min Act: -0.0001

Data Index: 399272 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6063. Min Act: -0.0001

Data Index: 1071824 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5434. Min Act: -0.0001

Data Index: 758144 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5241. Min Act: -0.0001

Data Index: 354651 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5569. Min Act: -0.0001

Data Index: 83695 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5104. Min Act: -0.0001

Data Index: 823834 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5649. Min Act: -0.0001

Data Index: 864436 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5382. Min Act: -0.0001

Data Index: 1304637 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5371. Min Act: -0.0001

Data Index: 1191662 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5165. Min Act: -0.0001

Data Index: 1318155 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5201. Min Act: -0.0001

Data Index: 1212058 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5668. Min Act: -0.0001

Data Index: 924466 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5040. Min Act: -0.0001

Data Index: 766044 (C4 (Web Text))

Max Activating Token Index: 282