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

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

Neuron 4985 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.9884. Min Act: -0.0000

Data Index: 633982 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.9615. Min Act: -0.0000

Data Index: 317100 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.8238. Min Act: -0.0000

Data Index: 751940 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 2.0235. Min Range: -2.0235

Max Act: 2.0235. Min Act: -0.0000

Data Index: 1044382 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.9012. Min Act: -0.0000

Data Index: 1277281 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.9410. Min Act: -0.0000

Data Index: 1110805 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.8457. Min Act: -0.0000

Data Index: 1358454 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.8366. Min Act: -0.0000

Data Index: 756319 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.9180. Min Act: -0.0000

Data Index: 1176528 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.7722. Min Act: -0.0000

Data Index: 1156369 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.8787. Min Act: -0.0000

Data Index: 330308 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.8510. Min Act: -0.0000

Data Index: 268445 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.6795. Min Act: -0.0000

Data Index: 1002342 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.5295. Min Act: -0.0000

Data Index: 900367 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.4760. Min Act: -0.0000

Data Index: 664707 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.4465. Min Act: -0.0000

Data Index: 571855 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1650343 (Python Code)

Max Activating Token Index: 982

Text #17

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.4594. Min Act: -0.0000

Data Index: 202928 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.4479. Min Act: -0.0000

Data Index: 1253644 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 2.0235. Min Range: -2.0235

Max Act: 1.3551. Min Act: -0.0000

Data Index: 409266 (C4 (Web Text))

Max Activating Token Index: 459