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

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

Neuron 3695 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0071. Min Range: -1.0071

Max Act: 1.0071. Min Act: -0.0000

Data Index: 969617 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.9782. Min Act: -0.0000

Data Index: 1051001 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.8791. Min Act: -0.0000

Data Index: 78914 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1332068 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1061931 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.8017. Min Act: -0.0000

Data Index: 670158 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1108558 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.7539. Min Act: -0.0000

Data Index: 768252 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1116134 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.7461. Min Act: -0.0000

Data Index: 871999 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.7731. Min Act: -0.0000

Data Index: 998503 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1295995 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.7637. Min Act: -0.0000

Data Index: 871369 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.7247. Min Act: -0.0000

Data Index: 356980 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.7446. Min Act: -0.0000

Data Index: 1080500 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.7678. Min Act: -0.0000

Data Index: 298466 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.7642. Min Act: -0.0000

Data Index: 160022 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1263297 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.7364. Min Act: -0.0000

Data Index: 785948 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 1.0071. Min Range: -1.0071

Max Act: 0.7103. Min Act: -0.0000

Data Index: 82539 (C4 (Web Text))

Max Activating Token Index: 718