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

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

Neuron 1828 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: 1.6741. Min Range: -1.6741

Max Act: 1.6741. Min Act: -0.0002

Data Index: 1264802 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.6659. Min Act: -0.0002

Data Index: 793796 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.5729. Min Act: -0.0002

Data Index: 734276 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.5908. Min Act: -0.0002

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.5223. Min Act: -0.0002

Data Index: 19735 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.5649. Min Act: -0.0002

Data Index: 937852 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.5157. Min Act: -0.0002

Data Index: 123043 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.5364. Min Act: -0.0002

Data Index: 1337327 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.4672. Min Act: -0.0002

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.5297. Min Act: -0.0003

Data Index: 1270667 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.4463. Min Act: -0.0002

Data Index: 1047007 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.4456. Min Act: -0.0002

Data Index: 114161 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.4704. Min Act: -0.0002

Data Index: 1001549 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.4671. Min Act: -0.0002

Data Index: 1167974 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.4231. Min Act: -0.0002

Data Index: 385078 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.4502. Min Act: -0.0002

Data Index: 69136 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.4682. Min Act: -0.0002

Data Index: 152168 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.4160. Min Act: -0.0002

Data Index: 340501 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.4448. Min Act: -0.0003

Data Index: 552979 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.4851. Min Act: -0.0002

Data Index: 106069 (C4 (Web Text))

Max Activating Token Index: 703