Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2341 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.3758. Min Act: -0.0001

Data Index: 383882 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.4336. Min Act: -0.0001

Data Index: 863604 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.3757. Min Act: -0.0001

Data Index: 882619 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.3421. Min Act: -0.0001

Data Index: 806371 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.2427. Min Act: -0.0001

Data Index: 434789 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1873. Min Act: -0.0001

Data Index: 1040829 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.2923. Min Act: -0.0001

Data Index: 716136 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.3156. Min Act: -0.0001

Data Index: 479185 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.2277. Min Act: -0.0001

Data Index: 141767 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1340. Min Act: -0.0001

Data Index: 311612 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1799. Min Act: -0.0001

Data Index: 1932 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.0907. Min Act: -0.0001

Data Index: 1056222 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1962. Min Act: -0.0001

Data Index: 310794 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.0978. Min Act: -0.0001

Data Index: 266471 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.0337. Min Act: -0.0001

Data Index: 607823 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1089. Min Act: -0.0001

Data Index: 60555 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.0753. Min Act: -0.0001

Data Index: 166219 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.0993. Min Act: -0.0001

Data Index: 264613 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1284. Min Act: -0.0002

Data Index: 878013 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 1.4336. Min Range: -1.4336

Max Act: 0.9977. Min Act: -0.0001

Data Index: 136035 (C4 (Web Text))

Max Activating Token Index: 277