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

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

Neuron 4177 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.9073. Min Act: -0.0000

Data Index: 111578 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.9651. Min Act: -0.0000

Data Index: 1188197 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.8850. Min Act: -0.0000

Data Index: 82652 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.8511. Min Act: -0.0000

Data Index: 70122 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.7467. Min Act: -0.0000

Data Index: 262843 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.7448. Min Act: -0.0000

Data Index: 128810 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.6112. Min Act: -0.0000

Data Index: 1025215 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.7041. Min Act: -0.0000

Data Index: 880426 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.6167. Min Act: -0.0000

Data Index: 1020340 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.6093. Min Act: -0.0000

Data Index: 256717 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.7699. Min Act: -0.0000

Data Index: 782487 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.5854. Min Act: -0.0000

Data Index: 1168236 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.6758. Min Act: -0.0000

Data Index: 774997 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.6433. Min Act: -0.0000

Data Index: 965456 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.6470. Min Act: -0.0000

Data Index: 1321404 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.6748. Min Act: -0.0000

Data Index: 1277696 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.5658. Min Act: -0.0000

Data Index: 429658 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.6547. Min Act: -0.0000

Data Index: 32280 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.6514. Min Act: -0.0000

Data Index: 875833 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 1.9651. Min Range: -1.9651

Max Act: 1.7540. Min Act: -0.0000

Data Index: 748018 (C4 (Web Text))

Max Activating Token Index: 976