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

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

Neuron 33 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2269. Min Act: -0.0002

Data Index: 1313681 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2294. Min Act: -0.0002

Data Index: 1060887 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2225. Min Act: -0.0002

Data Index: 1311128 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2143. Min Act: -0.0002

Data Index: 198398 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2165. Min Act: -0.0002

Data Index: 826261 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2128. Min Act: -0.0002

Data Index: 468806 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2151. Min Act: -0.0002

Data Index: 34350 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2098. Min Act: -0.0002

Data Index: 432467 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2096. Min Act: -0.0002

Data Index: 1344515 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2104. Min Act: -0.0002

Data Index: 204030 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2135. Min Act: -0.0002

Data Index: 262199 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2099. Min Act: -0.0002

Data Index: 1176499 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2043. Min Act: -0.0002

Data Index: 98604 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2091. Min Act: -0.0003

Data Index: 1310539 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2075. Min Act: -0.0002

Data Index: 1306645 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2036. Min Act: -0.0002

Data Index: 438937 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2021. Min Act: -0.0003

Data Index: 1327008 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2060. Min Act: -0.0002

Data Index: 1093682 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2038. Min Act: -0.0002

Data Index: 1225355 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2011. Min Act: -0.0002

Data Index: 1180674 (C4 (Web Text))

Max Activating Token Index: 146