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

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

Neuron 1721 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4560. Min Range: -2.4560

Max Act: 2.4560. Min Act: -0.0000

Data Index: 703426 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.5183. Min Act: -0.0000

Data Index: 649534 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.6113. Min Act: -0.0000

Data Index: 1334606 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.3784. Min Act: -0.0000

Data Index: 114570 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.3404. Min Act: -0.0000

Data Index: 860521 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1232600 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.3264. Min Act: -0.0000

Data Index: 546789 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.3873. Min Act: -0.0000

Data Index: 321152 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.2147. Min Act: -0.0000

Data Index: 184635 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.2881. Min Act: -0.0000

Data Index: 197602 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.3144. Min Act: -0.0000

Data Index: 17264 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.2047. Min Act: -0.0000

Data Index: 978809 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.2428. Min Act: -0.0000

Data Index: 814858 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.2595. Min Act: -0.0000

Data Index: 1101652 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.2710. Min Act: -0.0000

Data Index: 1122600 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.2331. Min Act: -0.0000

Data Index: 893699 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.2303. Min Act: -0.0000

Data Index: 1098021 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.3212. Min Act: -0.0000

Data Index: 522292 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.3291. Min Act: -0.0000

Data Index: 312772 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 2.4560. Min Range: -2.4560

Max Act: 1.1820. Min Act: -0.0000

Data Index: 174593 (C4 (Web Text))

Max Activating Token Index: 93