Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1087 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0088. Min Range: -1.0088

Max Act: 1.0065. Min Act: -0.0001

Data Index: 371921 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 1.0088. Min Range: -1.0088

Max Act: 1.0088. Min Act: -0.0001

Data Index: 865558 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9128. Min Act: -0.0001

Data Index: 1000499 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.8515. Min Act: -0.0001

Data Index: 462287 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.7446. Min Act: -0.0001

Data Index: 696515 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.7504. Min Act: -0.0001

Data Index: 275233 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.7932. Min Act: -0.0001

Data Index: 1031267 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.7561. Min Act: -0.0001

Data Index: 458474 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.7274. Min Act: -0.0001

Data Index: 544598 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.7420. Min Act: -0.0001

Data Index: 1191306 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.6987. Min Act: -0.0001

Data Index: 1109641 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.7711. Min Act: -0.0001

Data Index: 851995 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.7281. Min Act: -0.0001

Data Index: 685627 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.7625. Min Act: -0.0001

Data Index: 179222 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.7246. Min Act: -0.0001

Data Index: 501439 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.7257. Min Act: -0.0001

Data Index: 24514 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.6729. Min Act: -0.0001

Data Index: 1132161 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.6610. Min Act: -0.0001

Data Index: 760224 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.6695. Min Act: -0.0001

Data Index: 1326708 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.6480. Min Act: -0.0001

Data Index: 54194 (C4 (Web Text))

Max Activating Token Index: 814