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

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

Neuron 1085 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: 0.3560. Min Range: -0.3560

Max Act: 0.3295. Min Act: -0.0000

Data Index: 369755 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3560. Min Act: -0.0000

Data Index: 58032 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3193. Min Act: -0.0000

Data Index: 683158 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1095970 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3144. Min Act: -0.0000

Data Index: 630149 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3000. Min Act: -0.0000

Data Index: 85278 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3002. Min Act: -0.0000

Data Index: 441295 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2889. Min Act: -0.0000

Data Index: 1159693 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1310905 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2844. Min Act: -0.0000

Data Index: 561882 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2714. Min Act: -0.0000

Data Index: 797776 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2627. Min Act: -0.0000

Data Index: 822833 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1139575 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2802. Min Act: -0.0000

Data Index: 870013 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2444. Min Act: -0.0000

Data Index: 683073 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2659. Min Act: -0.0000

Data Index: 280553 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2663. Min Act: -0.0000

Data Index: 309936 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2635. Min Act: -0.0000

Data Index: 40828 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2691. Min Act: -0.0000

Data Index: 818170 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2573. Min Act: -0.0000

Data Index: 151550 (C4 (Web Text))

Max Activating Token Index: 990