Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3851 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0777. Min Act: -0.0001

Data Index: 337884 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0777. Min Act: -0.0001

Data Index: 954492 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0781. Min Act: -0.0001

Data Index: 344567 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1276512 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1246778 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0764. Min Act: -0.0001

Data Index: 696492 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0703. Min Act: -0.0001

Data Index: 364237 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1136654 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1188907 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1322246 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0680. Min Act: -0.0001

Data Index: 359480 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0708. Min Act: -0.0001

Data Index: 541262 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1174544 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0606. Min Act: -0.0001

Data Index: 1077897 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0628. Min Act: -0.0001

Data Index: 718503 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1286338 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1199134 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1157085 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0590. Min Act: -0.0001

Data Index: 87230 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0633. Min Act: -0.0000

Data Index: 730156 (C4 (Web Text))

Max Activating Token Index: 478