Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1200 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.9637. Min Act: -0.0001

Data Index: 126779 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.8934. Min Act: -0.0001

Data Index: 761603 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7944. Min Act: -0.0001

Data Index: 264564 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.8076. Min Act: -0.0001

Data Index: 323225 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7756. Min Act: -0.0001

Data Index: 483481 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7883. Min Act: -0.0001

Data Index: 24818 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.8355. Min Act: -0.0001

Data Index: 542727 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7958. Min Act: -0.0001

Data Index: 1172564 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7712. Min Act: -0.0001

Data Index: 1055886 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7221. Min Act: -0.0001

Data Index: 428968 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7894. Min Act: -0.0001

Data Index: 1276762 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7824. Min Act: -0.0001

Data Index: 348227 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7271. Min Act: -0.0001

Data Index: 1013687 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7508. Min Act: -0.0001

Data Index: 1201061 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7039. Min Act: -0.0001

Data Index: 1297732 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7474. Min Act: -0.0001

Data Index: 1046056 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7374. Min Act: -0.0001

Data Index: 1328596 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7365. Min Act: -0.0001

Data Index: 518384 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7132. Min Act: -0.0001

Data Index: 1202870 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.9637. Min Range: -0.9637

Max Act: 0.7586. Min Act: -0.0001

Data Index: 1094431 (C4 (Web Text))

Max Activating Token Index: 301