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

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

Neuron 789 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1313. Min Act: -0.0001

Data Index: 711519 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1108. Min Act: -0.0001

Data Index: 1287397 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1137. Min Act: -0.0000

Data Index: 889236 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1115. Min Act: -0.0000

Data Index: 725957 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1268930 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1082. Min Act: -0.0000

Data Index: 793693 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1027. Min Act: -0.0001

Data Index: 325862 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1015. Min Act: -0.0000

Data Index: 345579 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1171147 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1029. Min Act: -0.0000

Data Index: 655031 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1024. Min Act: -0.0000

Data Index: 773122 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0983. Min Act: -0.0000

Data Index: 142986 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1041. Min Act: -0.0000

Data Index: 958898 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1016. Min Act: -0.0000

Data Index: 803632 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0950. Min Act: -0.0001

Data Index: 716187 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1021396 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0919. Min Act: -0.0000

Data Index: 839657 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1109197 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0898. Min Act: -0.0001

Data Index: 1327261 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0922. Min Act: -0.0000

Data Index: 1076176 (C4 (Web Text))

Max Activating Token Index: 624