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

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

Neuron 2579 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3442. Min Act: -0.0000

Data Index: 953047 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3401. Min Act: -0.0000

Data Index: 404792 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2898. Min Act: 0.0001

Data Index: 61113 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2673. Min Act: -0.0001

Data Index: 1553474 (Python Code)

Max Activating Token Index: 556

Text #4

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2631. Min Act: -0.0000

Data Index: 503926 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2439. Min Act: -0.0000

Data Index: 24162 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2482. Min Act: -0.0000

Data Index: 546666 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2561. Min Act: -0.0000

Data Index: 833562 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2428. Min Act: -0.0000

Data Index: 519871 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2402. Min Act: 0.0001

Data Index: 1269470 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2423. Min Act: -0.0000

Data Index: 598008 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2265. Min Act: -0.0000

Data Index: 26585 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2431. Min Act: -0.0000

Data Index: 812808 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2148. Min Act: -0.0000

Data Index: 649546 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2217. Min Act: -0.0001

Data Index: 800626 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2429. Min Act: -0.0000

Data Index: 241494 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2340. Min Act: -0.0000

Data Index: 519955 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2163. Min Act: -0.0000

Data Index: 840865 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2091. Min Act: -0.0001

Data Index: 627200 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2225. Min Act: -0.0001

Data Index: 1194973 (C4 (Web Text))

Max Activating Token Index: 380