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

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

Neuron 1458 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: 0.3896. Min Range: -0.3896

Max Act: 0.3448. Min Act: -0.0001

Data Index: 25234 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3138. Min Act: -0.0001

Data Index: 759332 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3896. Min Act: -0.0001

Data Index: 843788 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3279. Min Act: -0.0001

Data Index: 152280 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3400. Min Act: -0.0001

Data Index: 365836 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3256. Min Act: -0.0001

Data Index: 678308 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3156. Min Act: -0.0001

Data Index: 573143 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.2842. Min Act: -0.0001

Data Index: 1231253 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.2716. Min Act: -0.0001

Data Index: 1099210 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3279. Min Act: -0.0001

Data Index: 1154372 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3020. Min Act: -0.0001

Data Index: 985294 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.2939. Min Act: -0.0001

Data Index: 1110682 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.3011. Min Act: -0.0001

Data Index: 270342 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.2920. Min Act: -0.0001

Data Index: 785474 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.2884. Min Act: -0.0001

Data Index: 683457 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.2656. Min Act: -0.0000

Data Index: 427889 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.2889. Min Act: -0.0001

Data Index: 279416 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.2672. Min Act: -0.0001

Data Index: 1022589 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.2550. Min Act: -0.0001

Data Index: 220495 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.3896. Min Range: -0.3896

Max Act: 0.2546. Min Act: -0.0001

Data Index: 866053 (C4 (Web Text))

Max Activating Token Index: 812