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

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

Neuron 4703 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: 0.7228. Min Range: -0.7228

Max Act: 0.7228. Min Act: -0.0000

Data Index: 250980 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.6899. Min Act: -0.0000

Data Index: 980089 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1290541 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.6093. Min Act: -0.0000

Data Index: 1272572 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.6147. Min Act: -0.0000

Data Index: 542013 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.5248. Min Act: -0.0000

Data Index: 609093 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.5045. Min Act: -0.0000

Data Index: 633346 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.4858. Min Act: -0.0000

Data Index: 986821 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.4994. Min Act: -0.0000

Data Index: 503904 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.4828. Min Act: -0.0000

Data Index: 763542 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1171492 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.4345. Min Act: -0.0000

Data Index: 757379 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.4330. Min Act: -0.0000

Data Index: 157558 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1301329 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.4487. Min Act: -0.0000

Data Index: 1294384 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.4346. Min Act: -0.0000

Data Index: 230748 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.4723. Min Act: -0.0000

Data Index: 954485 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.4510. Min Act: -0.0000

Data Index: 24593 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1199811 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.4207. Min Act: -0.0000

Data Index: 905121 (C4 (Web Text))

Max Activating Token Index: 551