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

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

Neuron 5341 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1535. Min Range: -1.1535

Max Act: 1.1535. Min Act: -0.0000

Data Index: 287881 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 1.1535. Min Range: -1.1535

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1032727 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 1.1535. Min Range: -1.1535

Max Act: 1.0765. Min Act: -0.0000

Data Index: 1275805 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 1.1535. Min Range: -1.1535

Max Act: 1.0581. Min Act: -0.0000

Data Index: 351307 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.9022. Min Act: -0.0000

Data Index: 211216 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1341267 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.9205. Min Act: -0.0000

Data Index: 988869 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.9003. Min Act: -0.0000

Data Index: 271972 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1241198 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.9572. Min Act: -0.0000

Data Index: 112032 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.8396. Min Act: -0.0000

Data Index: 929677 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.8943. Min Act: -0.0000

Data Index: 533778 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.8778. Min Act: -0.0000

Data Index: 376771 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.9284. Min Act: -0.0000

Data Index: 559266 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1132539 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1247553 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1060530 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.7921. Min Act: -0.0000

Data Index: 7192 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.7848. Min Act: -0.0000

Data Index: 190676 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.8292. Min Act: -0.0000

Data Index: 553956 (C4 (Web Text))

Max Activating Token Index: 500