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

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

Neuron 3982 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.4228. Min Act: -0.0001

Data Index: 123303 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.4642. Min Act: -0.0000

Data Index: 677698 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.3845. Min Act: -0.0001

Data Index: 260689 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.3674. Min Act: -0.0001

Data Index: 1125410 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.4926. Min Act: -0.0001

Data Index: 609450 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.3298. Min Act: -0.0001

Data Index: 100769 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.3187. Min Act: -0.0000

Data Index: 300129 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.3661. Min Act: -0.0001

Data Index: 1194648 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.3134. Min Act: -0.0001

Data Index: 581892 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.3163. Min Act: -0.0001

Data Index: 999348 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.2510. Min Act: -0.0000

Data Index: 1024896 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.1833. Min Act: -0.0001

Data Index: 1133181 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.2777. Min Act: -0.0001

Data Index: 1108791 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.2449. Min Act: -0.0001

Data Index: 619057 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.3148. Min Act: -0.0001

Data Index: 511642 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.2097. Min Act: -0.0001

Data Index: 650588 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.3212. Min Act: -0.0001

Data Index: 444664 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.2858. Min Act: -0.0001

Data Index: 289849 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.1814. Min Act: -0.0000

Data Index: 155399 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.1999. Min Act: -0.0001

Data Index: 883339 (C4 (Web Text))

Max Activating Token Index: 622