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

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

Neuron 1753 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1150. Min Act: -0.0001

Data Index: 896383 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1038. Min Act: -0.0001

Data Index: 277422 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1025. Min Act: -0.0001

Data Index: 135454 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1019. Min Act: -0.0001

Data Index: 1221929 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1018. Min Act: -0.0001

Data Index: 411240 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0942. Min Act: -0.0001

Data Index: 632570 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0978. Min Act: -0.0001

Data Index: 982601 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0957. Min Act: -0.0001

Data Index: 378109 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0919. Min Act: -0.0001

Data Index: 299195 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0877. Min Act: -0.0001

Data Index: 378517 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0961. Min Act: -0.0001

Data Index: 317826 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0929. Min Act: -0.0001

Data Index: 408018 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0925. Min Act: -0.0001

Data Index: 281001 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1257261 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0870. Min Act: -0.0001

Data Index: 614404 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0909. Min Act: -0.0001

Data Index: 348575 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0909. Min Act: -0.0001

Data Index: 113271 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1119279 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0886. Min Act: -0.0001

Data Index: 944971 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0889. Min Act: -0.0001

Data Index: 159104 (C4 (Web Text))

Max Activating Token Index: 545