Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3046 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.5910. Min Range: -3.5910

Max Act: 3.5410. Min Act: -0.0001

Data Index: 1183402 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 3.5910. Min Range: -3.5910

Max Act: 3.5910. Min Act: -0.0002

Data Index: 313239 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 3.5910. Min Range: -3.5910

Max Act: 2.9980. Min Act: -0.0002

Data Index: 878835 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 3.5910. Min Range: -3.5910

Max Act: 3.2265. Min Act: -0.0001

Data Index: 936363 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 3.5910. Min Range: -3.5910

Max Act: 3.1913. Min Act: -0.0002

Data Index: 906728 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 3.5910. Min Range: -3.5910

Max Act: 3.0416. Min Act: -0.0001

Data Index: 745265 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 3.5910. Min Range: -3.5910

Max Act: 2.8294. Min Act: -0.0002

Data Index: 1032806 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 3.5910. Min Range: -3.5910

Max Act: 2.9574. Min Act: -0.0001

Data Index: 397627 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 3.5910. Min Range: -3.5910

Max Act: 2.8807. Min Act: -0.0001

Data Index: 214748 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 3.5910. Min Range: -3.5910

Max Act: 2.8455. Min Act: -0.0001

Data Index: 1189675 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 3.5910. Min Range: -3.5910

Max Act: 2.8362. Min Act: -0.0001

Data Index: 337787 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 3.5910. Min Range: -3.5910

Max Act: 2.5411. Min Act: -0.0001

Data Index: 1339438 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 3.5910. Min Range: -3.5910

Max Act: 2.7774. Min Act: -0.0002

Data Index: 809529 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 3.5910. Min Range: -3.5910

Max Act: 2.7615. Min Act: -0.0001

Data Index: 447981 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 3.5910. Min Range: -3.5910

Max Act: 2.8433. Min Act: -0.0002

Data Index: 9448 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 3.5910. Min Range: -3.5910

Max Act: 2.8259. Min Act: -0.0002

Data Index: 412673 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 3.5910. Min Range: -3.5910

Max Act: 2.6844. Min Act: -0.0002

Data Index: 1045612 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 3.5910. Min Range: -3.5910

Max Act: 2.7758. Min Act: -0.0002

Data Index: 973355 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 3.5910. Min Range: -3.5910

Max Act: 2.8045. Min Act: -0.0002

Data Index: 297003 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 3.5910. Min Range: -3.5910

Max Act: 2.2718. Min Act: -0.0002

Data Index: 343766 (C4 (Web Text))

Max Activating Token Index: 305