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

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

Neuron 3551 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2981. Min Act: -0.0003

Data Index: 346506 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.1968. Min Act: -0.0002

Data Index: 1146292 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0523. Min Act: -0.0003

Data Index: 449316 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0523. Min Act: -0.0003

Data Index: 590601 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0482. Min Act: -0.0003

Data Index: 1321712 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0165. Min Act: -0.0003

Data Index: 192692 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9577. Min Act: -0.0003

Data Index: 1189371 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9888. Min Act: -0.0003

Data Index: 1032875 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9233. Min Act: -0.0003

Data Index: 587259 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9445. Min Act: -0.0003

Data Index: 809126 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9401. Min Act: -0.0003

Data Index: 1222260 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9385. Min Act: -0.0003

Data Index: 1235373 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9049. Min Act: -0.0003

Data Index: 1304434 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9063. Min Act: -0.0003

Data Index: 1280463 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9264. Min Act: -0.0003

Data Index: 1001929 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8989. Min Act: -0.0003

Data Index: 642561 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8972. Min Act: -0.0003

Data Index: 83256 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9238. Min Act: -0.0003

Data Index: 733791 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9481. Min Act: -0.0003

Data Index: 124742 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9184. Min Act: -0.0003

Data Index: 528859 (C4 (Web Text))

Max Activating Token Index: 389