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

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

Neuron 4154 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.1110. Min Act: -0.0000

Data Index: 1006594 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.2375. Min Act: -0.0000

Data Index: 722684 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.3441. Min Act: -0.0000

Data Index: 336752 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.7563. Min Act: -0.0000

Data Index: 966002 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.6010. Min Act: -0.0000

Data Index: 990806 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.6603. Min Act: -0.0000

Data Index: 657088 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.7805. Min Act: -0.0000

Data Index: 770290 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.4962. Min Act: -0.0000

Data Index: 728910 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.5016. Min Act: -0.0000

Data Index: 519084 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.4817. Min Act: -0.0000

Data Index: 157490 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.7338. Min Act: -0.0000

Data Index: 642417 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.4205. Min Act: -0.0000

Data Index: 250665 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.5285. Min Act: -0.0000

Data Index: 177939 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.5395. Min Act: -0.0000

Data Index: 1351235 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.5096. Min Act: -0.0000

Data Index: 315112 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.5806. Min Act: -0.0000

Data Index: 311046 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.4599. Min Act: -0.0000

Data Index: 106448 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.3144. Min Act: -0.0000

Data Index: 395146 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.4126. Min Act: -0.0000

Data Index: 712948 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 3.3441. Min Range: -3.3441

Max Act: 2.2983. Min Act: -0.0000

Data Index: 252468 (C4 (Web Text))

Max Activating Token Index: 137