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

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

Neuron 4629 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: 0.8446. Min Range: -0.8446

Max Act: 0.8391. Min Act: -0.0002

Data Index: 719517 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.8446. Min Act: -0.0002

Data Index: 974946 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7984. Min Act: -0.0002

Data Index: 507284 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.8213. Min Act: -0.0002

Data Index: 414470 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.8050. Min Act: -0.0002

Data Index: 683679 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.8000. Min Act: -0.0002

Data Index: 591108 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7881. Min Act: -0.0002

Data Index: 1314260 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.8020. Min Act: -0.0002

Data Index: 843910 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7750. Min Act: -0.0002

Data Index: 990527 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7971. Min Act: -0.0002

Data Index: 135160 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7828. Min Act: -0.0002

Data Index: 1310893 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7877. Min Act: -0.0002

Data Index: 328359 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7911. Min Act: -0.0002

Data Index: 1012870 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7740. Min Act: -0.0002

Data Index: 1175852 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7643. Min Act: -0.0002

Data Index: 1008049 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7644. Min Act: -0.0002

Data Index: 180862 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7575. Min Act: -0.0002

Data Index: 81244 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7372. Min Act: -0.0003

Data Index: 1266149 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7409. Min Act: -0.0002

Data Index: 1284174 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.8446. Min Range: -0.8446

Max Act: 0.7427. Min Act: -0.0002

Data Index: 54389 (C4 (Web Text))

Max Activating Token Index: 192