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

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

Neuron 4374 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: 0.6857. Min Range: -0.6857

Max Act: 0.6857. Min Act: -0.0000

Data Index: 85981 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5910. Min Act: -0.0000

Data Index: 672316 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.6071. Min Act: -0.0000

Data Index: 970531 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5959. Min Act: -0.0000

Data Index: 385214 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5825. Min Act: -0.0000

Data Index: 224892 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5383. Min Act: -0.0000

Data Index: 504136 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1232562 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5664. Min Act: -0.0000

Data Index: 299925 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5597. Min Act: -0.0000

Data Index: 770988 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5757. Min Act: -0.0000

Data Index: 754572 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5519. Min Act: -0.0000

Data Index: 493316 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5562. Min Act: -0.0000

Data Index: 717528 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5576. Min Act: -0.0000

Data Index: 998587 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5502. Min Act: -0.0000

Data Index: 81902 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5454. Min Act: -0.0000

Data Index: 331380 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5236. Min Act: -0.0000

Data Index: 369747 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5245. Min Act: -0.0000

Data Index: 65172 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5744. Min Act: -0.0000

Data Index: 150659 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5342. Min Act: -0.0000

Data Index: 962805 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.6857. Min Range: -0.6857

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1021699 (C4 (Web Text))

Max Activating Token Index: 34