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

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

Neuron 905 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.2907. Min Act: -0.0000

Data Index: 549873 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.7490. Min Act: -0.0000

Data Index: 321575 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.6980. Min Act: -0.0000

Data Index: 640263 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.9548. Min Act: -0.0000

Data Index: 548842 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.9559. Min Act: -0.0000

Data Index: 525481 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.9123. Min Act: -0.0000

Data Index: 633923 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.7793. Min Act: -0.0000

Data Index: 889770 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.6225. Min Act: -0.0000

Data Index: 982350 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.7366. Min Act: -0.0000

Data Index: 714718 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.6511. Min Act: -0.0000

Data Index: 414085 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.6331. Min Act: -0.0000

Data Index: 294511 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.5842. Min Act: -0.0000

Data Index: 163048 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.6998. Min Act: -0.0000

Data Index: 263833 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.4268. Min Act: -0.0000

Data Index: 260539 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.4059. Min Act: -0.0000

Data Index: 680264 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.6446. Min Act: -0.0000

Data Index: 641764 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.6354. Min Act: -0.0000

Data Index: 819713 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.3629. Min Act: -0.0000

Data Index: 4206 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.4280. Min Act: -0.0000

Data Index: 403649 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 3.2907. Min Range: -3.2907

Max Act: 2.4379. Min Act: -0.0000

Data Index: 454127 (C4 (Web Text))

Max Activating Token Index: 559