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

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

Neuron 3500 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9007. Min Range: -2.9007

Max Act: 2.9007. Min Act: -0.0000

Data Index: 49817 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 2.9007. Min Range: -2.9007

Max Act: 2.7481. Min Act: -0.0000

Data Index: 958330 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 2.9007. Min Range: -2.9007

Max Act: 2.5979. Min Act: -0.0000

Data Index: 273198 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 2.9007. Min Range: -2.9007

Max Act: 2.8435. Min Act: -0.0000

Data Index: 699082 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 2.9007. Min Range: -2.9007

Max Act: 2.6096. Min Act: -0.0000

Data Index: 547264 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 2.9007. Min Range: -2.9007

Max Act: 2.6854. Min Act: -0.0000

Data Index: 1295514 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 2.9007. Min Range: -2.9007

Max Act: 2.6705. Min Act: -0.0000

Data Index: 917010 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 2.9007. Min Range: -2.9007

Max Act: 2.1205. Min Act: -0.0000

Data Index: 1359520 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.9414. Min Act: -0.0000

Data Index: 277470 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.9078. Min Act: -0.0000

Data Index: 1024646 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.9685. Min Act: -0.0000

Data Index: 717176 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.9505. Min Act: -0.0000

Data Index: 1262519 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.9089. Min Act: -0.0000

Data Index: 767129 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.7936. Min Act: -0.0000

Data Index: 1100219 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.8775. Min Act: -0.0000

Data Index: 896290 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.8043. Min Act: -0.0000

Data Index: 175171 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.6635. Min Act: -0.0000

Data Index: 1196255 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.6834. Min Act: -0.0000

Data Index: 842625 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.7590. Min Act: -0.0000

Data Index: 1016723 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.7230. Min Act: -0.0000

Data Index: 1219044 (C4 (Web Text))

Max Activating Token Index: 476