Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 494 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.7993. Min Act: -0.0002

Data Index: 426412 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.7746. Min Act: -0.0002

Data Index: 459386 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.7746. Min Act: -0.0002

Data Index: 220088 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6991. Min Act: -0.0002

Data Index: 449797 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6916. Min Act: -0.0002

Data Index: 647834 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6872. Min Act: -0.0002

Data Index: 846235 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6783. Min Act: -0.0002

Data Index: 393044 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6660. Min Act: -0.0002

Data Index: 706917 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6684. Min Act: -0.0002

Data Index: 1028048 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6244. Min Act: -0.0001

Data Index: 1287738 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6280. Min Act: -0.0002

Data Index: 983731 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6166. Min Act: -0.0002

Data Index: 441161 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6035. Min Act: -0.0002

Data Index: 50657 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6007. Min Act: -0.0002

Data Index: 1022317 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6183. Min Act: -0.0002

Data Index: 435043 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6179. Min Act: -0.0001

Data Index: 922868 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6547. Min Act: -0.0001

Data Index: 1025594 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.5864. Min Act: -0.0002

Data Index: 639629 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6146. Min Act: -0.0002

Data Index: 1235215 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6316. Min Act: -0.0001

Data Index: 804732 (C4 (Web Text))

Max Activating Token Index: 811