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

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

Neuron 3945 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.5121. Min Act: -0.0001

Data Index: 1288748 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.4895. Min Act: -0.0001

Data Index: 1037535 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.2961. Min Act: -0.0001

Data Index: 666091 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.1765. Min Act: -0.0001

Data Index: 1300274 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.1984. Min Act: -0.0001

Data Index: 805475 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.2382. Min Act: -0.0001

Data Index: 848969 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.1385. Min Act: -0.0001

Data Index: 1016338 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.1639. Min Act: -0.0001

Data Index: 789944 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.1665. Min Act: -0.0001

Data Index: 469641 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.1266. Min Act: -0.0001

Data Index: 288310 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.1246. Min Act: -0.0001

Data Index: 245934 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.0925. Min Act: -0.0001

Data Index: 244773 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.1311. Min Act: -0.0001

Data Index: 520210 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 1.5121. Min Range: -1.5121

Max Act: 0.9993. Min Act: -0.0001

Data Index: 848424 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.0864. Min Act: -0.0001

Data Index: 604644 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.0556. Min Act: -0.0001

Data Index: 982457 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.0708. Min Act: -0.0001

Data Index: 1109483 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.1055. Min Act: -0.0001

Data Index: 230180 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.0562. Min Act: -0.0001

Data Index: 366662 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 1.5121. Min Range: -1.5121

Max Act: 1.0553. Min Act: -0.0001

Data Index: 1080313 (C4 (Web Text))

Max Activating Token Index: 449