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

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

Neuron 2372 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: 1.3931. Min Range: -1.3931

Max Act: 1.3931. Min Act: -0.0002

Data Index: 931285 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.3600. Min Act: -0.0002

Data Index: 337698 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.3020. Min Act: -0.0003

Data Index: 309207 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.3320. Min Act: -0.0002

Data Index: 1125410 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.3043. Min Act: -0.0002

Data Index: 118062 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.3031. Min Act: -0.0002

Data Index: 342163 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.3035. Min Act: -0.0002

Data Index: 6287 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2969. Min Act: -0.0002

Data Index: 1062537 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2729. Min Act: -0.0002

Data Index: 401729 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2363. Min Act: -0.0002

Data Index: 806238 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2481. Min Act: -0.0002

Data Index: 95057 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2158. Min Act: -0.0002

Data Index: 721903 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2470. Min Act: -0.0002

Data Index: 847017 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2293. Min Act: -0.0003

Data Index: 1357071 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2143. Min Act: -0.0002

Data Index: 1250822 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2225. Min Act: -0.0002

Data Index: 1196188 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2199. Min Act: -0.0002

Data Index: 19272 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2379. Min Act: -0.0002

Data Index: 344988 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2006. Min Act: -0.0003

Data Index: 919702 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.1940. Min Act: -0.0002

Data Index: 1319540 (C4 (Web Text))

Max Activating Token Index: 943