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

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

Neuron 3160 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.6249. Min Act: -0.0000

Data Index: 72724 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5590. Min Act: -0.0000

Data Index: 841531 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5213. Min Act: -0.0000

Data Index: 585195 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1145128 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5215. Min Act: -0.0000

Data Index: 59139 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4533. Min Act: -0.0000

Data Index: 438693 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4539. Min Act: -0.0000

Data Index: 295338 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1131454 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4392. Min Act: -0.0000

Data Index: 780568 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4302. Min Act: -0.0000

Data Index: 715981 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4154. Min Act: -0.0000

Data Index: 670052 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1293968 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4166. Min Act: -0.0000

Data Index: 600315 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1129988 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1013730 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.3907. Min Act: 0.0000

Data Index: 463310 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4133. Min Act: -0.0000

Data Index: 13315 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.3732. Min Act: -0.0000

Data Index: 975894 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1167075 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.3914. Min Act: -0.0000

Data Index: 395571 (C4 (Web Text))

Max Activating Token Index: 840