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

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

Neuron 2147 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9746. Min Range: -1.9746

Max Act: 1.9746. Min Act: -0.0000

Data Index: 97208 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 1.9746. Min Range: -1.9746

Max Act: 1.7990. Min Act: -0.0000

Data Index: 497198 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 1.9746. Min Range: -1.9746

Max Act: 1.5570. Min Act: -0.0000

Data Index: 651182 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 1.9746. Min Range: -1.9746

Max Act: 1.4385. Min Act: -0.0000

Data Index: 317408 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 1.9746. Min Range: -1.9746

Max Act: 1.3397. Min Act: -0.0000

Data Index: 179441 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 1.9746. Min Range: -1.9746

Max Act: 1.2181. Min Act: -0.0000

Data Index: 596694 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 1.9746. Min Range: -1.9746

Max Act: 1.1349. Min Act: -0.0000

Data Index: 320423 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 1.9746. Min Range: -1.9746

Max Act: 0.9318. Min Act: -0.0000

Data Index: 320236 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 1.9746. Min Range: -1.9746

Max Act: 0.9946. Min Act: -0.0000

Data Index: 1138477 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 1.9746. Min Range: -1.9746

Max Act: 0.9100. Min Act: -0.0000

Data Index: 1297601 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 1.9746. Min Range: -1.9746

Max Act: 0.8720. Min Act: -0.0000

Data Index: 202629 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 1.9746. Min Range: -1.9746

Max Act: 0.9753. Min Act: -0.0000

Data Index: 266860 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 1.9746. Min Range: -1.9746

Max Act: 0.9525. Min Act: -0.0000

Data Index: 982979 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 1.9746. Min Range: -1.9746

Max Act: 0.9112. Min Act: -0.0000

Data Index: 194844 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 1.9746. Min Range: -1.9746

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1071121 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 1.9746. Min Range: -1.9746

Max Act: 0.8991. Min Act: -0.0000

Data Index: 1125601 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 1.9746. Min Range: -1.9746

Max Act: 0.9213. Min Act: -0.0000

Data Index: 801692 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 1.9746. Min Range: -1.9746

Max Act: 0.8904. Min Act: -0.0000

Data Index: 83239 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 1.9746. Min Range: -1.9746

Max Act: 0.8928. Min Act: -0.0000

Data Index: 177902 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 1.9746. Min Range: -1.9746

Max Act: 0.8508. Min Act: -0.0000

Data Index: 990332 (C4 (Web Text))

Max Activating Token Index: 552