Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2853 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.4536. Min Act: -0.0001

Data Index: 502072 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.3673. Min Act: -0.0001

Data Index: 578869 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.3243. Min Act: -0.0001

Data Index: 796505 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.3475. Min Act: -0.0001

Data Index: 1303242 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.3456. Min Act: -0.0001

Data Index: 1254825 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.3152. Min Act: -0.0001

Data Index: 1277776 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.2733. Min Act: -0.0001

Data Index: 37329 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.3341. Min Act: -0.0001

Data Index: 783458 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.2577. Min Act: -0.0001

Data Index: 1369423 (Python Code)

Max Activating Token Index: 820

Text #9

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.2976. Min Act: -0.0001

Data Index: 813490 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.3110. Min Act: -0.0001

Data Index: 722216 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.2474. Min Act: -0.0001

Data Index: 41055 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.2494. Min Act: -0.0001

Data Index: 1022631 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.2166. Min Act: -0.0001

Data Index: 626045 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.1973. Min Act: -0.0001

Data Index: 466694 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.2294. Min Act: -0.0001

Data Index: 742267 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.1948. Min Act: -0.0001

Data Index: 807295 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.2299. Min Act: -0.0001

Data Index: 877105 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.2125. Min Act: -0.0001

Data Index: 625032 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 1.4536. Min Range: -1.4536

Max Act: 1.2135. Min Act: -0.0001

Data Index: 247690 (C4 (Web Text))

Max Activating Token Index: 826