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

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

Neuron 1466 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.8947. Min Act: -0.0001

Data Index: 1326656 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.3262. Min Act: -0.0001

Data Index: 1312439 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.4689. Min Act: -0.0001

Data Index: 176732 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.1263. Min Act: -0.0001

Data Index: 1290861 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.3025. Min Act: -0.0001

Data Index: 558857 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.3923. Min Act: -0.0001

Data Index: 149362 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.2254. Min Act: -0.0001

Data Index: 721976 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.3117. Min Act: -0.0001

Data Index: 961653 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 3.8947. Min Range: -3.8947

Max Act: 2.9236. Min Act: -0.0001

Data Index: 1130559 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.1497. Min Act: -0.0001

Data Index: 749378 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 3.8947. Min Range: -3.8947

Max Act: 2.8137. Min Act: -0.0001

Data Index: 1124931 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 3.8947. Min Range: -3.8947

Max Act: 2.9595. Min Act: -0.0001

Data Index: 837734 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 3.8947. Min Range: -3.8947

Max Act: 2.9284. Min Act: -0.0001

Data Index: 508014 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 3.8947. Min Range: -3.8947

Max Act: 2.7742. Min Act: -0.0001

Data Index: 65531 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 3.8947. Min Range: -3.8947

Max Act: 2.9228. Min Act: -0.0001

Data Index: 365317 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 3.8947. Min Range: -3.8947

Max Act: 2.9143. Min Act: -0.0001

Data Index: 1258642 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 3.8947. Min Range: -3.8947

Max Act: 2.9071. Min Act: -0.0001

Data Index: 116262 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 3.8947. Min Range: -3.8947

Max Act: 2.8708. Min Act: -0.0001

Data Index: 423068 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 3.8947. Min Range: -3.8947

Max Act: 2.8818. Min Act: -0.0001

Data Index: 208173 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 3.8947. Min Range: -3.8947

Max Act: 2.8558. Min Act: -0.0001

Data Index: 125894 (C4 (Web Text))

Max Activating Token Index: 289