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

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

Neuron 5837 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1200737 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.9330. Min Act: -0.0000

Data Index: 362443 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1656680 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.7845. Min Act: -0.0000

Data Index: 39861 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.7373. Min Act: -0.0000

Data Index: 57311 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.7413. Min Act: -0.0000

Data Index: 929043 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.7251. Min Act: -0.0000

Data Index: 457473 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6877. Min Act: -0.0000

Data Index: 316895 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1151796 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1316232 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1044720 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6120. Min Act: -0.0000

Data Index: 1337959 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6418. Min Act: -0.0000

Data Index: 228034 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1329289 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1645770 (Python Code)

Max Activating Token Index: 288

Text #15

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6226. Min Act: -0.0000

Data Index: 222880 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6367. Min Act: -0.0000

Data Index: 632403 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.5875. Min Act: -0.0000

Data Index: 696021 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6044. Min Act: -0.0000

Data Index: 478080 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6038. Min Act: -0.0000

Data Index: 392078 (C4 (Web Text))

Max Activating Token Index: 355