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

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

Neuron 2773 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.6163. Min Act: -0.0000

Data Index: 815149 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.6013. Min Act: -0.0001

Data Index: 116420 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5161. Min Act: -0.0001

Data Index: 507409 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.3742. Min Act: -0.0001

Data Index: 645863 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.3617. Min Act: -0.0000

Data Index: 282274 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.3350. Min Act: -0.0000

Data Index: 757950 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.3305. Min Act: -0.0000

Data Index: 243422 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.3273. Min Act: -0.0001

Data Index: 702371 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.3271. Min Act: -0.0000

Data Index: 846287 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.3214. Min Act: -0.0000

Data Index: 277777 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.3357. Min Act: -0.0000

Data Index: 257680 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.2881. Min Act: -0.0000

Data Index: 160401 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.2978. Min Act: -0.0000

Data Index: 936160 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.3026. Min Act: -0.0000

Data Index: 135636 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.2868. Min Act: -0.0000

Data Index: 866956 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.2869. Min Act: -0.0000

Data Index: 872238 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.2828. Min Act: -0.0000

Data Index: 341730 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1141634 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1234515 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.2787. Min Act: -0.0000

Data Index: 104321 (C4 (Web Text))

Max Activating Token Index: 869