Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1594 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.5699. Min Act: -0.0000

Data Index: 93327 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.4837. Min Act: -0.0000

Data Index: 742815 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.3678. Min Act: -0.0000

Data Index: 244843 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.3983. Min Act: -0.0000

Data Index: 1144414 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.3969. Min Act: -0.0000

Data Index: 240350 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.2985. Min Act: -0.0000

Data Index: 868316 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.1591. Min Act: -0.0000

Data Index: 1464761 (Python Code)

Max Activating Token Index: 245

Text #7

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.1975. Min Act: -0.0000

Data Index: 1134962 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.2924. Min Act: -0.0000

Data Index: 1556795 (Python Code)

Max Activating Token Index: 800

Text #9

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.1344. Min Act: -0.0001

Data Index: 1374493 (Python Code)

Max Activating Token Index: 323

Text #10

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.1156. Min Act: -0.0000

Data Index: 853935 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.1137. Min Act: -0.0000

Data Index: 314798 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.1685. Min Act: -0.0000

Data Index: 339967 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1129362 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.0718. Min Act: -0.0000

Data Index: 1233648 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.9594. Min Act: -0.0000

Data Index: 557833 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.0335. Min Act: -0.0000

Data Index: 183354 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.1292. Min Act: -0.0000

Data Index: 80787 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.9887. Min Act: -0.0000

Data Index: 1249323 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.9933. Min Act: -0.0000

Data Index: 83153 (C4 (Web Text))

Max Activating Token Index: 369