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

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

Neuron 1534 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: 1.0991. Min Range: -1.0991

Max Act: 1.0991. Min Act: -0.0003

Data Index: 845157 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.9851. Min Act: -0.0002

Data Index: 402715 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.9808. Min Act: -0.0002

Data Index: 19281 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.9777. Min Act: -0.0002

Data Index: 141317 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.9682. Min Act: -0.0003

Data Index: 1299822 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.9460. Min Act: -0.0002

Data Index: 329541 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.9362. Min Act: -0.0002

Data Index: 222139 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.9613. Min Act: -0.0003

Data Index: 444015 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.9358. Min Act: -0.0002

Data Index: 730131 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.9271. Min Act: -0.0002

Data Index: 886843 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.9315. Min Act: -0.0003

Data Index: 511467 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.9211. Min Act: -0.0003

Data Index: 867618 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.9019. Min Act: -0.0003

Data Index: 668270 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.9093. Min Act: -0.0003

Data Index: 172407 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.9178. Min Act: -0.0002

Data Index: 720975 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.9012. Min Act: -0.0002

Data Index: 1281536 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.8817. Min Act: -0.0003

Data Index: 1115705 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.8825. Min Act: -0.0002

Data Index: 98327 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.8575. Min Act: -0.0002

Data Index: 608914 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 1.0991. Min Range: -1.0991

Max Act: 0.8887. Min Act: -0.0002

Data Index: 830663 (C4 (Web Text))

Max Activating Token Index: 116