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

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

Neuron 4271 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.9857. Min Act: -0.0000

Data Index: 529771 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8679. Min Act: -0.0000

Data Index: 568264 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.9322. Min Act: -0.0000

Data Index: 857113 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.9419. Min Act: -0.0000

Data Index: 347795 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8583. Min Act: -0.0000

Data Index: 737029 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8498. Min Act: -0.0000

Data Index: 721390 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8491. Min Act: -0.0000

Data Index: 15288 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.9218. Min Act: -0.0000

Data Index: 878078 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1206055 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7954. Min Act: -0.0000

Data Index: 104353 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7840. Min Act: -0.0000

Data Index: 288676 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8036. Min Act: -0.0000

Data Index: 510620 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8220. Min Act: -0.0000

Data Index: 455372 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7320. Min Act: -0.0000

Data Index: 1341136 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7546. Min Act: -0.0000

Data Index: 406601 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1340943 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.6802. Min Act: -0.0000

Data Index: 235002 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7466. Min Act: -0.0000

Data Index: 836991 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7162. Min Act: -0.0000

Data Index: 141812 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7335. Min Act: -0.0000

Data Index: 781439 (C4 (Web Text))

Max Activating Token Index: 317