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

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

Neuron 1903 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: 0.2869. Min Range: -0.2869

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1032930 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2574. Min Act: -0.0000

Data Index: 578537 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2423. Min Act: -0.0000

Data Index: 74019 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2164. Min Act: -0.0000

Data Index: 580290 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2443. Min Act: -0.0000

Data Index: 14402 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2448. Min Act: -0.0000

Data Index: 586081 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2340. Min Act: -0.0000

Data Index: 569183 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2345. Min Act: -0.0000

Data Index: 1161135 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1247972 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2142. Min Act: -0.0000

Data Index: 1129968 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1318028 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2268. Min Act: -0.0000

Data Index: 633861 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1268303 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2235. Min Act: -0.0000

Data Index: 547018 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2157. Min Act: -0.0000

Data Index: 319748 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2082. Min Act: -0.0000

Data Index: 308410 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2215. Min Act: -0.0000

Data Index: 790577 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2061. Min Act: -0.0000

Data Index: 108391 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2136. Min Act: -0.0000

Data Index: 405398 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1185746 (C4 (Web Text))

Max Activating Token Index: 136