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

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

Neuron 2817 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.8744. Min Act: -0.0001

Data Index: 891291 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.8961. Min Act: -0.0001

Data Index: 1561127 (Python Code)

Max Activating Token Index: 671

Text #2

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.8167. Min Act: -0.0001

Data Index: 1602359 (Python Code)

Max Activating Token Index: 981

Text #3

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.8302. Min Act: -0.0001

Data Index: 1552204 (Python Code)

Max Activating Token Index: 472

Text #4

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7717. Min Act: -0.0001

Data Index: 1423576 (Python Code)

Max Activating Token Index: 653

Text #5

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7439. Min Act: -0.0001

Data Index: 1636886 (Python Code)

Max Activating Token Index: 514

Text #6

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7650. Min Act: -0.0001

Data Index: 1604926 (Python Code)

Max Activating Token Index: 823

Text #7

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7697. Min Act: -0.0001

Data Index: 48443 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7235. Min Act: -0.0001

Data Index: 1591205 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7031. Min Act: -0.0001

Data Index: 1495245 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7253. Min Act: -0.0001

Data Index: 1514340 (Python Code)

Max Activating Token Index: 156

Text #11

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7678. Min Act: -0.0001

Data Index: 1656397 (Python Code)

Max Activating Token Index: 170

Text #12

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7148. Min Act: -0.0001

Data Index: 1626800 (Python Code)

Max Activating Token Index: 76

Text #13

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7435. Min Act: -0.0001

Data Index: 1629263 (Python Code)

Max Activating Token Index: 993

Text #14

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.8236. Min Act: -0.0001

Data Index: 1593466 (Python Code)

Max Activating Token Index: 264

Text #15

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7280. Min Act: -0.0001

Data Index: 1526673 (Python Code)

Max Activating Token Index: 163

Text #16

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6602. Min Act: -0.0001

Data Index: 1653709 (Python Code)

Max Activating Token Index: 237

Text #17

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.7016. Min Act: -0.0001

Data Index: 1461570 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6948. Min Act: -0.0001

Data Index: 1621869 (Python Code)

Max Activating Token Index: 398

Text #19

Max Range: 0.8961. Min Range: -0.8961

Max Act: 0.6498. Min Act: -0.0001

Data Index: 1500090 (Python Code)

Max Activating Token Index: 947