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

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

Neuron 3641 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: 1.1250. Min Range: -1.1250

Max Act: 1.1250. Min Act: -0.0002

Data Index: 465685 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 1.1250. Min Range: -1.1250

Max Act: 1.0471. Min Act: -0.0002

Data Index: 652447 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 1.1250. Min Range: -1.1250

Max Act: 1.0352. Min Act: -0.0002

Data Index: 289707 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 1.1250. Min Range: -1.1250

Max Act: 1.0307. Min Act: -0.0003

Data Index: 832492 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.1250. Min Range: -1.1250

Max Act: 1.0196. Min Act: -0.0002

Data Index: 63356 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 1.1250. Min Range: -1.1250

Max Act: 1.0270. Min Act: -0.0002

Data Index: 1128207 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 1.1250. Min Range: -1.1250

Max Act: 1.0221. Min Act: -0.0003

Data Index: 1137854 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9832. Min Act: -0.0002

Data Index: 1339975 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9945. Min Act: -0.0002

Data Index: 778339 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 1.1250. Min Range: -1.1250

Max Act: 1.0039. Min Act: -0.0002

Data Index: 1303246 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9988. Min Act: -0.0003

Data Index: 757676 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9811. Min Act: -0.0002

Data Index: 576214 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9771. Min Act: -0.0002

Data Index: 484993 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 1.1250. Min Range: -1.1250

Max Act: 1.0089. Min Act: -0.0002

Data Index: 587301 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9681. Min Act: -0.0002

Data Index: 962015 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 1.1250. Min Range: -1.1250

Max Act: 1.0009. Min Act: -0.0002

Data Index: 480678 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9884. Min Act: -0.0002

Data Index: 559831 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9977. Min Act: -0.0002

Data Index: 515004 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9763. Min Act: -0.0002

Data Index: 993230 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9468. Min Act: -0.0003

Data Index: 323033 (C4 (Web Text))

Max Activating Token Index: 30