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

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

Neuron 4498 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.1633. Min Act: -0.0000

Data Index: 448977 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0796. Min Act: -0.0000

Data Index: 1009763 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0835. Min Act: -0.0000

Data Index: 237042 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9787. Min Act: -0.0000

Data Index: 105088 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0318. Min Act: -0.0000

Data Index: 141061 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9427. Min Act: -0.0000

Data Index: 458324 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1147829 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9266. Min Act: -0.0000

Data Index: 851564 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9077. Min Act: -0.0000

Data Index: 804950 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9419. Min Act: -0.0000

Data Index: 1116896 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8736. Min Act: -0.0000

Data Index: 556837 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7289. Min Act: -0.0000

Data Index: 908253 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8041. Min Act: -0.0000

Data Index: 617249 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8252. Min Act: -0.0000

Data Index: 138689 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8030. Min Act: -0.0000

Data Index: 232372 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1230227 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8062. Min Act: -0.0000

Data Index: 137495 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1152366 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7797. Min Act: -0.0000

Data Index: 363078 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7628. Min Act: -0.0000

Data Index: 585509 (C4 (Web Text))

Max Activating Token Index: 224