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

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

Neuron 3107 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: 1.4462. Min Range: -1.4462

Max Act: 1.4462. Min Act: -0.0003

Data Index: 133543 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4359. Min Act: -0.0002

Data Index: 1074587 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.1574. Min Act: -0.0002

Data Index: 165530 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.1199. Min Act: -0.0002

Data Index: 844314 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.1528. Min Act: -0.0002

Data Index: 313479 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.1366. Min Act: -0.0002

Data Index: 907950 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.0762. Min Act: -0.0003

Data Index: 260512 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.0445. Min Act: -0.0002

Data Index: 267288 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.0253. Min Act: -0.0002

Data Index: 878333 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.0433. Min Act: -0.0002

Data Index: 1346174 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.0058. Min Act: -0.0002

Data Index: 116243 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.0212. Min Act: -0.0002

Data Index: 128206 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.0215. Min Act: -0.0002

Data Index: 609613 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9817. Min Act: -0.0002

Data Index: 570379 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9836. Min Act: -0.0002

Data Index: 688069 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9918. Min Act: -0.0002

Data Index: 353588 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9834. Min Act: -0.0002

Data Index: 366407 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9746. Min Act: -0.0002

Data Index: 223360 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9971. Min Act: -0.0002

Data Index: 1331248 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9668. Min Act: -0.0002

Data Index: 959724 (C4 (Web Text))

Max Activating Token Index: 161