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

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

Neuron 3326 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: 1.0130. Min Range: -1.0130

Max Act: 1.0130. Min Act: -0.0000

Data Index: 1334638 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9492. Min Act: -0.0000

Data Index: 445773 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9743. Min Act: -0.0000

Data Index: 467610 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.8286. Min Act: -0.0000

Data Index: 45095 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1298878 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.8566. Min Act: -0.0000

Data Index: 231069 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.7794. Min Act: -0.0000

Data Index: 599494 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.7123. Min Act: -0.0000

Data Index: 94755 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6594. Min Act: -0.0000

Data Index: 987647 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.7254. Min Act: -0.0000

Data Index: 451408 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1225116 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6466. Min Act: -0.0000

Data Index: 152479 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6678. Min Act: -0.0000

Data Index: 812875 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6590. Min Act: -0.0000

Data Index: 173064 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6955. Min Act: -0.0000

Data Index: 193734 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6464. Min Act: -0.0000

Data Index: 305564 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6753. Min Act: -0.0000

Data Index: 930350 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1188746 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6163. Min Act: -0.0000

Data Index: 834384 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6288. Min Act: -0.0000

Data Index: 957763 (C4 (Web Text))

Max Activating Token Index: 192