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

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

Neuron 4714 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: 1.5613. Min Range: -1.5613

Max Act: 1.5613. Min Act: -0.0002

Data Index: 891341 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.5385. Min Act: -0.0002

Data Index: 149963 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.4774. Min Act: -0.0002

Data Index: 651219 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.4808. Min Act: -0.0003

Data Index: 62830 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.4444. Min Act: -0.0002

Data Index: 1422714 (Python Code)

Max Activating Token Index: 426

Text #5

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.3986. Min Act: -0.0002

Data Index: 797071 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.4228. Min Act: -0.0002

Data Index: 120216 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.4159. Min Act: -0.0002

Data Index: 584860 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.3995. Min Act: -0.0002

Data Index: 616287 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.3913. Min Act: -0.0002

Data Index: 126074 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.3779. Min Act: -0.0002

Data Index: 1280844 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.3922. Min Act: -0.0002

Data Index: 1474426 (Python Code)

Max Activating Token Index: 770

Text #12

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.3841. Min Act: -0.0002

Data Index: 1126719 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.3806. Min Act: -0.0002

Data Index: 823533 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.3449. Min Act: -0.0002

Data Index: 1599101 (Python Code)

Max Activating Token Index: 413

Text #15

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.3643. Min Act: -0.0002

Data Index: 251507 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.3382. Min Act: -0.0002

Data Index: 1464465 (Python Code)

Max Activating Token Index: 208

Text #17

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.3669. Min Act: -0.0002

Data Index: 983013 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.3556. Min Act: -0.0002

Data Index: 475637 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 1.5613. Min Range: -1.5613

Max Act: 1.3545. Min Act: -0.0002

Data Index: 1202901 (C4 (Web Text))

Max Activating Token Index: 311