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

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

Neuron 3704 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.4922. Min Act: -0.0000

Data Index: 1329974 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.3503. Min Act: -0.0000

Data Index: 561519 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.1124. Min Act: -0.0000

Data Index: 93660 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.1314. Min Act: -0.0000

Data Index: 174918 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.0108. Min Act: -0.0000

Data Index: 1290520 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.9713. Min Act: -0.0000

Data Index: 470384 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1103786 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.9261. Min Act: -0.0000

Data Index: 570864 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.8268. Min Act: -0.0000

Data Index: 478693 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1047938 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.7793. Min Act: -0.0000

Data Index: 839973 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1170863 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.8269. Min Act: -0.0000

Data Index: 165551 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.7473. Min Act: -0.0000

Data Index: 70821 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1258053 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.7333. Min Act: -0.0000

Data Index: 709554 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.7239. Min Act: -0.0000

Data Index: 358957 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.7437. Min Act: -0.0000

Data Index: 219032 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1112088 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.6222. Min Act: -0.0000

Data Index: 644683 (C4 (Web Text))

Max Activating Token Index: 291