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

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

Neuron 1784 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: 1.0909. Min Range: -1.0909

Max Act: 1.0909. Min Act: -0.0000

Data Index: 1244675 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 1.0909. Min Range: -1.0909

Max Act: 1.0127. Min Act: -0.0000

Data Index: 689733 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1009396 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.9969. Min Act: -0.0000

Data Index: 1309114 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.9669. Min Act: -0.0000

Data Index: 723081 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.8341. Min Act: -0.0000

Data Index: 853502 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.8031. Min Act: -0.0000

Data Index: 722987 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.8163. Min Act: -0.0000

Data Index: 506528 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1065413 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.7916. Min Act: -0.0000

Data Index: 183146 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.8039. Min Act: -0.0000

Data Index: 240675 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.8230. Min Act: -0.0000

Data Index: 503875 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1080690 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.7666. Min Act: -0.0000

Data Index: 935891 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.7603. Min Act: -0.0000

Data Index: 691760 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.7596. Min Act: -0.0000

Data Index: 656635 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.7341. Min Act: -0.0000

Data Index: 775912 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1313382 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.7455. Min Act: -0.0000

Data Index: 812006 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.7421. Min Act: -0.0000

Data Index: 599849 (C4 (Web Text))

Max Activating Token Index: 47