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

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

Neuron 5067 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: 3.7432. Min Range: -3.7432

Max Act: 3.7415. Min Act: -0.0000

Data Index: 611022 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 3.7432. Min Range: -3.7432

Max Act: 3.7432. Min Act: -0.0000

Data Index: 652215 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 3.7432. Min Range: -3.7432

Max Act: 3.1567. Min Act: -0.0000

Data Index: 300959 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 3.7432. Min Range: -3.7432

Max Act: 3.1103. Min Act: -0.0000

Data Index: 74449 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 3.7432. Min Range: -3.7432

Max Act: 3.4562. Min Act: -0.0000

Data Index: 417030 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 3.7432. Min Range: -3.7432

Max Act: 2.8350. Min Act: -0.0000

Data Index: 1176057 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 3.7432. Min Range: -3.7432

Max Act: 2.7423. Min Act: -0.0000

Data Index: 194126 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 3.7432. Min Range: -3.7432

Max Act: 2.5785. Min Act: -0.0000

Data Index: 1104841 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 3.7432. Min Range: -3.7432

Max Act: 2.6989. Min Act: -0.0000

Data Index: 914749 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 3.7432. Min Range: -3.7432

Max Act: 2.3135. Min Act: -0.0000

Data Index: 330740 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 3.7432. Min Range: -3.7432

Max Act: 2.8553. Min Act: -0.0000

Data Index: 240219 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 3.7432. Min Range: -3.7432

Max Act: 2.4279. Min Act: -0.0000

Data Index: 890213 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 3.7432. Min Range: -3.7432

Max Act: 2.5306. Min Act: -0.0000

Data Index: 578200 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 3.7432. Min Range: -3.7432

Max Act: 2.6420. Min Act: -0.0000

Data Index: 334397 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 3.7432. Min Range: -3.7432

Max Act: 2.4262. Min Act: -0.0000

Data Index: 140369 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 3.7432. Min Range: -3.7432

Max Act: 2.5171. Min Act: -0.0000

Data Index: 546225 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 3.7432. Min Range: -3.7432

Max Act: 2.5784. Min Act: -0.0000

Data Index: 1060014 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 3.7432. Min Range: -3.7432

Max Act: 2.3367. Min Act: -0.0000

Data Index: 1187763 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 3.7432. Min Range: -3.7432

Max Act: 2.5475. Min Act: -0.0000

Data Index: 410446 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 3.7432. Min Range: -3.7432

Max Act: 2.2278. Min Act: -0.0000

Data Index: 790452 (C4 (Web Text))

Max Activating Token Index: 687