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

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

Neuron 3594 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4335. Min Range: -1.4335

Max Act: 1.4335. Min Act: -0.0001

Data Index: 786166 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 1.4335. Min Range: -1.4335

Max Act: 1.1923. Min Act: -0.0001

Data Index: 938417 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 1.4335. Min Range: -1.4335

Max Act: 1.1880. Min Act: -0.0001

Data Index: 253301 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 1.4335. Min Range: -1.4335

Max Act: 1.1206. Min Act: -0.0001

Data Index: 431630 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 1.4335. Min Range: -1.4335

Max Act: 1.0662. Min Act: -0.0001

Data Index: 343885 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 1.4335. Min Range: -1.4335

Max Act: 1.0905. Min Act: -0.0001

Data Index: 638428 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 1.4335. Min Range: -1.4335

Max Act: 1.0699. Min Act: -0.0001

Data Index: 229992 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 1.4335. Min Range: -1.4335

Max Act: 1.0038. Min Act: -0.0001

Data Index: 825621 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 1.4335. Min Range: -1.4335

Max Act: 1.0936. Min Act: -0.0001

Data Index: 150037 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 1.4335. Min Range: -1.4335

Max Act: 1.0645. Min Act: -0.0001

Data Index: 1119443 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 1.4335. Min Range: -1.4335

Max Act: 1.0194. Min Act: -0.0001

Data Index: 926971 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 1.4335. Min Range: -1.4335

Max Act: 1.0735. Min Act: -0.0001

Data Index: 190691 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 1.4335. Min Range: -1.4335

Max Act: 1.0405. Min Act: -0.0001

Data Index: 325653 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 1.4335. Min Range: -1.4335

Max Act: 1.0054. Min Act: -0.0001

Data Index: 8299 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 1.4335. Min Range: -1.4335

Max Act: 1.0217. Min Act: -0.0001

Data Index: 761335 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 1.4335. Min Range: -1.4335

Max Act: 0.9770. Min Act: -0.0001

Data Index: 372548 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 1.4335. Min Range: -1.4335

Max Act: 0.9370. Min Act: -0.0001

Data Index: 659801 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 1.4335. Min Range: -1.4335

Max Act: 0.9109. Min Act: -0.0001

Data Index: 838065 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 1.4335. Min Range: -1.4335

Max Act: 0.9336. Min Act: -0.0001

Data Index: 852121 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 1.4335. Min Range: -1.4335

Max Act: 0.9311. Min Act: -0.0001

Data Index: 1097542 (C4 (Web Text))

Max Activating Token Index: 87