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

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

Neuron 161 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1256069 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3797. Min Act: -0.0000

Data Index: 299623 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1222626 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1203042 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3493. Min Act: -0.0000

Data Index: 1287069 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3357. Min Act: -0.0000

Data Index: 424009 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3265. Min Act: -0.0000

Data Index: 1039279 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3440. Min Act: -0.0000

Data Index: 801725 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3348. Min Act: -0.0000

Data Index: 171996 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1041920 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1139393 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3149. Min Act: -0.0000

Data Index: 430542 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1224896 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1018956 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3303. Min Act: -0.0000

Data Index: 254152 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1194764 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.2958. Min Act: -0.0000

Data Index: 693550 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3146. Min Act: -0.0000

Data Index: 448568 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3116. Min Act: -0.0000

Data Index: 1175520 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.2998. Min Act: -0.0000

Data Index: 230303 (C4 (Web Text))

Max Activating Token Index: 574