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

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

Neuron 4060 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: 0.6384. Min Range: -0.6384

Max Act: 0.6384. Min Act: -0.0000

Data Index: 283679 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1067342 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.6324. Min Act: -0.0000

Data Index: 360762 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.6043. Min Act: -0.0000

Data Index: 211007 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.6212. Min Act: -0.0000

Data Index: 262289 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1643159 (Python Code)

Max Activating Token Index: 797

Text #6

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.5299. Min Act: -0.0000

Data Index: 342637 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1090803 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.5363. Min Act: -0.0000

Data Index: 880231 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.5325. Min Act: -0.0000

Data Index: 931680 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.5152. Min Act: -0.0000

Data Index: 103918 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.5338. Min Act: -0.0000

Data Index: 929840 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.5031. Min Act: -0.0000

Data Index: 396071 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.5141. Min Act: -0.0000

Data Index: 806767 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4787. Min Act: -0.0000

Data Index: 112255 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4899. Min Act: -0.0000

Data Index: 198268 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4848. Min Act: -0.0000

Data Index: 854070 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4457. Min Act: -0.0000

Data Index: 292217 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4481. Min Act: -0.0000

Data Index: 377917 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.6384. Min Range: -0.6384

Max Act: 0.4681. Min Act: -0.0000

Data Index: 956266 (C4 (Web Text))

Max Activating Token Index: 53