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

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

Neuron 4370 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: 2.0308. Min Range: -2.0308

Max Act: 2.0308. Min Act: -0.0002

Data Index: 840454 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.7487. Min Act: -0.0002

Data Index: 1192090 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.6947. Min Act: -0.0002

Data Index: 935048 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.6315. Min Act: -0.0002

Data Index: 368436 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.6215. Min Act: -0.0002

Data Index: 223525 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.6185. Min Act: -0.0002

Data Index: 1000347 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.5982. Min Act: -0.0002

Data Index: 481584 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.6083. Min Act: -0.0002

Data Index: 1249528 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.6139. Min Act: -0.0002

Data Index: 1248532 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.5912. Min Act: -0.0002

Data Index: 358283 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.5831. Min Act: -0.0002

Data Index: 295655 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.5616. Min Act: -0.0002

Data Index: 423467 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.5536. Min Act: -0.0002

Data Index: 1282825 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.5633. Min Act: -0.0002

Data Index: 1273371 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.5474. Min Act: -0.0002

Data Index: 292175 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.5539. Min Act: -0.0002

Data Index: 959575 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.5531. Min Act: -0.0003

Data Index: 314936 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.5421. Min Act: -0.0003

Data Index: 748369 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.5536. Min Act: -0.0002

Data Index: 1231424 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 2.0308. Min Range: -2.0308

Max Act: 1.5442. Min Act: -0.0002

Data Index: 1291901 (C4 (Web Text))

Max Activating Token Index: 834