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

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

Neuron 2278 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4200. Min Range: -1.4200

Max Act: 1.4200. Min Act: -0.0001

Data Index: 502659 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 1.4200. Min Range: -1.4200

Max Act: 1.2524. Min Act: -0.0001

Data Index: 753302 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 1.4200. Min Range: -1.4200

Max Act: 1.2040. Min Act: -0.0002

Data Index: 1027801 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 1.4200. Min Range: -1.4200

Max Act: 1.0645. Min Act: -0.0001

Data Index: 649465 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 1.4200. Min Range: -1.4200

Max Act: 1.1006. Min Act: -0.0001

Data Index: 1005015 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.9633. Min Act: -0.0001

Data Index: 1160623 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.9589. Min Act: -0.0001

Data Index: 1033155 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.9470. Min Act: -0.0002

Data Index: 984869 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.9632. Min Act: -0.0002

Data Index: 198194 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 1.4200. Min Range: -1.4200

Max Act: 1.0648. Min Act: -0.0001

Data Index: 961464 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.9866. Min Act: -0.0001

Data Index: 746664 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.9480. Min Act: -0.0001

Data Index: 362307 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.9734. Min Act: -0.0002

Data Index: 465478 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.9105. Min Act: -0.0001

Data Index: 787507 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.9825. Min Act: -0.0001

Data Index: 1106908 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.9552. Min Act: -0.0001

Data Index: 1214241 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.9501. Min Act: -0.0002

Data Index: 817732 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.9445. Min Act: -0.0001

Data Index: 921034 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.9116. Min Act: -0.0001

Data Index: 1178544 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 1.4200. Min Range: -1.4200

Max Act: 0.9409. Min Act: -0.0001

Data Index: 1138283 (C4 (Web Text))

Max Activating Token Index: 322