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

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

Neuron 6141 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.0075. Min Act: -0.0000

Data Index: 721239 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.4975. Min Act: -0.0000

Data Index: 452890 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.0480. Min Act: -0.0000

Data Index: 1471575 (Python Code)

Max Activating Token Index: 700

Text #3

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.0928. Min Act: -0.0000

Data Index: 1567537 (Python Code)

Max Activating Token Index: 1006

Text #4

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.3233. Min Act: -0.0000

Data Index: 457332 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.1442. Min Act: -0.0000

Data Index: 481929 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.8827. Min Act: -0.0000

Data Index: 1380366 (Python Code)

Max Activating Token Index: 830

Text #7

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.6486. Min Act: -0.0000

Data Index: 476968 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.7496. Min Act: -0.0000

Data Index: 1323890 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.9354. Min Act: -0.0000

Data Index: 857144 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.8141. Min Act: -0.0000

Data Index: 1415435 (Python Code)

Max Activating Token Index: 724

Text #11

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.9101. Min Act: -0.0000

Data Index: 1082538 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.8145. Min Act: -0.0000

Data Index: 1426307 (Python Code)

Max Activating Token Index: 57

Text #13

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.7882. Min Act: -0.0000

Data Index: 257553 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.6040. Min Act: -0.0000

Data Index: 1351143 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.8815. Min Act: -0.0000

Data Index: 1369438 (Python Code)

Max Activating Token Index: 946

Text #16

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.7709. Min Act: -0.0000

Data Index: 1095312 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.8567. Min Act: -0.0000

Data Index: 725739 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.6414. Min Act: -0.0000

Data Index: 970018 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.8280. Min Act: -0.0000

Data Index: 667702 (C4 (Web Text))

Max Activating Token Index: 912