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

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

Neuron 1601 in Layer 0

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: 0.4514. Min Range: -0.4514

Max Act: 0.4514. Min Act: -0.0001

Data Index: 801137 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4096. Min Act: -0.0001

Data Index: 743461 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3849. Min Act: -0.0001

Data Index: 428070 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3934. Min Act: -0.0001

Data Index: 923617 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3795. Min Act: -0.0001

Data Index: 1318372 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3673. Min Act: -0.0001

Data Index: 81283 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3741. Min Act: -0.0001

Data Index: 701632 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3660. Min Act: -0.0001

Data Index: 468491 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3707. Min Act: -0.0001

Data Index: 159215 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3701. Min Act: -0.0001

Data Index: 346106 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3604. Min Act: -0.0001

Data Index: 511094 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3572. Min Act: -0.0001

Data Index: 161177 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3537. Min Act: -0.0001

Data Index: 242000 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3441. Min Act: -0.0001

Data Index: 962669 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3490. Min Act: -0.0001

Data Index: 423558 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3358. Min Act: -0.0001

Data Index: 501254 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3331. Min Act: -0.0002

Data Index: 341018 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3343. Min Act: -0.0001

Data Index: 923466 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3325. Min Act: -0.0001

Data Index: 1357783 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3317. Min Act: -0.0001

Data Index: 1251617 (C4 (Web Text))

Max Activating Token Index: 75