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

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

Neuron 353 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2668. Min Act: -0.0000

Data Index: 737316 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2818. Min Act: -0.0000

Data Index: 1236231 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2762. Min Act: -0.0000

Data Index: 281657 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2538. Min Act: -0.0000

Data Index: 654702 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1317881 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1253745 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2312. Min Act: -0.0000

Data Index: 121368 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2390. Min Act: -0.0000

Data Index: 959137 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2444. Min Act: -0.0000

Data Index: 318207 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1204454 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2302. Min Act: -0.0000

Data Index: 962582 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2231. Min Act: -0.0000

Data Index: 607397 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2108. Min Act: -0.0000

Data Index: 30283 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1072378 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2133. Min Act: -0.0000

Data Index: 735377 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1017196 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2073. Min Act: -0.0000

Data Index: 107662 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1325891 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.2031. Min Act: -0.0000

Data Index: 843951 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.2818. Min Range: -0.2818

Max Act: 0.1868. Min Act: -0.0000

Data Index: 371251 (C4 (Web Text))

Max Activating Token Index: 699