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

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

Neuron 5545 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: 0.7270. Min Range: -0.7270

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1150553 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1201485 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.7270. Min Act: -0.0000

Data Index: 347611 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1289740 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6746. Min Act: -0.0000

Data Index: 755729 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1117660 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6700. Min Act: -0.0000

Data Index: 641436 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6914. Min Act: -0.0000

Data Index: 267973 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6270. Min Act: -0.0001

Data Index: 1240719 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6452. Min Act: -0.0000

Data Index: 457558 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6673. Min Act: -0.0000

Data Index: 808230 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6865. Min Act: -0.0000

Data Index: 62497 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1158663 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6580. Min Act: -0.0000

Data Index: 218193 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6555. Min Act: -0.0000

Data Index: 656384 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1180527 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6488. Min Act: -0.0001

Data Index: 265899 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6762. Min Act: -0.0000

Data Index: 891786 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1321910 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6681. Min Act: -0.0000

Data Index: 946107 (C4 (Web Text))

Max Activating Token Index: 532