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

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

Neuron 638 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.5522. Min Act: -0.0001

Data Index: 527762 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.4793. Min Act: -0.0001

Data Index: 562982 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.4218. Min Act: -0.0001

Data Index: 142546 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.4896. Min Act: -0.0001

Data Index: 344084 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.3932. Min Act: -0.0001

Data Index: 483304 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.3399. Min Act: -0.0001

Data Index: 1201478 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.2296. Min Act: -0.0001

Data Index: 656001 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.2131. Min Act: -0.0001

Data Index: 302675 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.2874. Min Act: -0.0001

Data Index: 1167413 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.2866. Min Act: -0.0001

Data Index: 947900 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.2629. Min Act: -0.0001

Data Index: 5097 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.3051. Min Act: -0.0001

Data Index: 1288426 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.3268. Min Act: -0.0001

Data Index: 766576 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.2540. Min Act: -0.0001

Data Index: 305653 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.1222. Min Act: -0.0001

Data Index: 585378 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.2249. Min Act: -0.0001

Data Index: 197721 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.0717. Min Act: -0.0001

Data Index: 459698 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 1.5522. Min Range: -1.5522

Max Act: 0.9931. Min Act: -0.0001

Data Index: 105861 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.0467. Min Act: -0.0001

Data Index: 514480 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 1.5522. Min Range: -1.5522

Max Act: 1.1857. Min Act: -0.0001

Data Index: 646771 (C4 (Web Text))

Max Activating Token Index: 17