Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3332 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.2516. Min Act: -0.0001

Data Index: 939546 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.0951. Min Act: -0.0001

Data Index: 1046108 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.1508. Min Act: -0.0001

Data Index: 536765 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.0653. Min Act: -0.0001

Data Index: 1255797 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.0924. Min Act: -0.0001

Data Index: 199138 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.0896. Min Act: -0.0001

Data Index: 962191 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.0036. Min Act: -0.0001

Data Index: 288896 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9950. Min Act: -0.0001

Data Index: 1314307 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9939. Min Act: -0.0001

Data Index: 1108766 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.0435. Min Act: -0.0001

Data Index: 11308 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9815. Min Act: -0.0001

Data Index: 845442 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.0075. Min Act: -0.0001

Data Index: 15396 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9539. Min Act: -0.0001

Data Index: 730135 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9788. Min Act: -0.0001

Data Index: 1155716 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9762. Min Act: -0.0001

Data Index: 1343671 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9435. Min Act: -0.0001

Data Index: 1252112 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9725. Min Act: -0.0001

Data Index: 817525 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9353. Min Act: -0.0001

Data Index: 700020 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9314. Min Act: -0.0001

Data Index: 4091 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9841. Min Act: -0.0001

Data Index: 249717 (C4 (Web Text))

Max Activating Token Index: 570