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

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

Neuron 2108 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7029. Min Range: -3.7029

Max Act: 3.6296. Min Act: -0.0000

Data Index: 1172383 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 3.7029. Min Range: -3.7029

Max Act: 3.7029. Min Act: -0.0000

Data Index: 923331 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.6973. Min Act: -0.0000

Data Index: 665882 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.4031. Min Act: -0.0000

Data Index: 820139 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 3.7029. Min Range: -3.7029

Max Act: 3.0146. Min Act: -0.0000

Data Index: 546757 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.4419. Min Act: -0.0000

Data Index: 16456 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.6746. Min Act: -0.0000

Data Index: 1043351 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.7906. Min Act: -0.0000

Data Index: 834136 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.6026. Min Act: -0.0000

Data Index: 1088961 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.5858. Min Act: -0.0000

Data Index: 427116 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.5449. Min Act: -0.0000

Data Index: 395630 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.5054. Min Act: -0.0000

Data Index: 1355638 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.4718. Min Act: -0.0000

Data Index: 21796 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.4459. Min Act: -0.0000

Data Index: 932275 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.3726. Min Act: -0.0000

Data Index: 1313851 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.2365. Min Act: -0.0000

Data Index: 932207 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.2443. Min Act: -0.0000

Data Index: 1250973 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.2088. Min Act: -0.0000

Data Index: 731035 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.1898. Min Act: -0.0000

Data Index: 675831 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 3.7029. Min Range: -3.7029

Max Act: 2.1673. Min Act: -0.0000

Data Index: 947860 (C4 (Web Text))

Max Activating Token Index: 112