Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5545 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3093. Min Range: -1.3093

Max Act: 1.3093. Min Act: -0.0000

Data Index: 321540 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 1.3093. Min Range: -1.3093

Max Act: 1.0797. Min Act: -0.0000

Data Index: 669382 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 1.3093. Min Range: -1.3093

Max Act: 1.0721. Min Act: -0.0000

Data Index: 264825 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 1.3093. Min Range: -1.3093

Max Act: 1.0957. Min Act: -0.0000

Data Index: 941667 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.9920. Min Act: -0.0000

Data Index: 648402 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.8227. Min Act: -0.0000

Data Index: 151531 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.7443. Min Act: -0.0000

Data Index: 568407 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.7669. Min Act: -0.0000

Data Index: 892780 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.7844. Min Act: -0.0000

Data Index: 92259 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.7279. Min Act: -0.0000

Data Index: 196348 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.7286. Min Act: -0.0000

Data Index: 1149258 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.7165. Min Act: -0.0000

Data Index: 588570 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1155216 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.7536. Min Act: -0.0000

Data Index: 778297 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.6742. Min Act: -0.0000

Data Index: 409918 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.6937. Min Act: -0.0000

Data Index: 490425 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.6714. Min Act: -0.0000

Data Index: 580160 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.6774. Min Act: -0.0000

Data Index: 1250152 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.6456. Min Act: -0.0000

Data Index: 513991 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 1.3093. Min Range: -1.3093

Max Act: 0.6611. Min Act: -0.0000

Data Index: 70265 (C4 (Web Text))

Max Activating Token Index: 503