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

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

Neuron 1267 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: 1.7171. Min Range: -1.7171

Max Act: 1.7171. Min Act: -0.0003

Data Index: 1286861 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.7158. Min Act: -0.0002

Data Index: 683350 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.6169. Min Act: -0.0002

Data Index: 796547 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.6173. Min Act: -0.0003

Data Index: 295810 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.5643. Min Act: -0.0003

Data Index: 668811 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.6375. Min Act: -0.0002

Data Index: 432566 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.5765. Min Act: -0.0002

Data Index: 257442 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.5673. Min Act: -0.0002

Data Index: 909871 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.5591. Min Act: -0.0002

Data Index: 232258 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.5223. Min Act: -0.0002

Data Index: 1294995 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.4457. Min Act: -0.0002

Data Index: 954458 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.4527. Min Act: -0.0002

Data Index: 814374 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.4794. Min Act: -0.0002

Data Index: 1249209 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.4799. Min Act: -0.0003

Data Index: 1094140 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.4951. Min Act: -0.0002

Data Index: 579160 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.4676. Min Act: -0.0003

Data Index: 690957 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.4961. Min Act: -0.0002

Data Index: 575606 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.4488. Min Act: -0.0003

Data Index: 1226560 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.4655. Min Act: -0.0002

Data Index: 239090 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.4590. Min Act: -0.0002

Data Index: 1300842 (C4 (Web Text))

Max Activating Token Index: 69