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

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

Neuron 2648 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: 0.3858. Min Range: -0.3858

Max Act: 0.3858. Min Act: -0.0002

Data Index: 884117 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3811. Min Act: -0.0002

Data Index: 1314144 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3847. Min Act: -0.0002

Data Index: 1283381 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3754. Min Act: -0.0002

Data Index: 510257 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3611. Min Act: -0.0002

Data Index: 847532 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3553. Min Act: -0.0002

Data Index: 637021 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3571. Min Act: -0.0002

Data Index: 359571 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3553. Min Act: -0.0002

Data Index: 763769 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3488. Min Act: -0.0002

Data Index: 764811 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3552. Min Act: -0.0002

Data Index: 584248 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3491. Min Act: -0.0002

Data Index: 1443279 (Python Code)

Max Activating Token Index: 287

Text #11

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3552. Min Act: -0.0002

Data Index: 1222332 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3509. Min Act: -0.0002

Data Index: 321833 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3521. Min Act: -0.0002

Data Index: 581701 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3523. Min Act: -0.0002

Data Index: 1175865 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3467. Min Act: -0.0002

Data Index: 306548 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3486. Min Act: -0.0002

Data Index: 286834 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3441. Min Act: -0.0002

Data Index: 1288331 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3524. Min Act: -0.0002

Data Index: 983495 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.3858. Min Range: -0.3858

Max Act: 0.3411. Min Act: -0.0002

Data Index: 320982 (C4 (Web Text))

Max Activating Token Index: 581