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

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

Neuron 5934 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.9321. Min Act: -0.0002

Data Index: 946335 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.8562. Min Act: -0.0002

Data Index: 515301 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.7739. Min Act: -0.0002

Data Index: 977977 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.9088. Min Act: -0.0002

Data Index: 193016 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.7391. Min Act: -0.0002

Data Index: 115074 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.7207. Min Act: -0.0002

Data Index: 48928 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.7319. Min Act: -0.0002

Data Index: 131911 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.7206. Min Act: -0.0002

Data Index: 66910 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.7088. Min Act: -0.0002

Data Index: 391556 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.6991. Min Act: -0.0002

Data Index: 454471 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.6929. Min Act: -0.0003

Data Index: 56036 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.6613. Min Act: -0.0002

Data Index: 673511 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.6995. Min Act: -0.0003

Data Index: 721195 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.6331. Min Act: -0.0002

Data Index: 498074 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.6758. Min Act: -0.0003

Data Index: 1042446 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.6754. Min Act: -0.0003

Data Index: 851329 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.6269. Min Act: -0.0002

Data Index: 818077 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.6717. Min Act: -0.0002

Data Index: 1331108 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.6632. Min Act: -0.0002

Data Index: 426541 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 1.9321. Min Range: -1.9321

Max Act: 1.6160. Min Act: -0.0002

Data Index: 804518 (C4 (Web Text))

Max Activating Token Index: 868