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

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

Neuron 5180 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: 4.8457. Min Range: -4.8457

Max Act: 4.6958. Min Act: -0.0000

Data Index: 791764 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 4.8457. Min Range: -4.8457

Max Act: 4.8457. Min Act: -0.0000

Data Index: 909755 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 4.8457. Min Range: -4.8457

Max Act: 4.3377. Min Act: -0.0000

Data Index: 294011 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 4.8457. Min Range: -4.8457

Max Act: 4.4347. Min Act: -0.0000

Data Index: 1206723 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 4.8457. Min Range: -4.8457

Max Act: 4.3662. Min Act: -0.0000

Data Index: 575137 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 4.8457. Min Range: -4.8457

Max Act: 4.1633. Min Act: -0.0000

Data Index: 1208887 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 4.8457. Min Range: -4.8457

Max Act: 4.3384. Min Act: -0.0000

Data Index: 642119 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 4.8457. Min Range: -4.8457

Max Act: 3.9604. Min Act: -0.0000

Data Index: 1343200 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 4.8457. Min Range: -4.8457

Max Act: 4.2417. Min Act: -0.0000

Data Index: 82473 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 4.8457. Min Range: -4.8457

Max Act: 3.8740. Min Act: -0.0000

Data Index: 1315546 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 4.8457. Min Range: -4.8457

Max Act: 3.9799. Min Act: -0.0000

Data Index: 1265339 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 4.8457. Min Range: -4.8457

Max Act: 3.9831. Min Act: -0.0000

Data Index: 390170 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 4.8457. Min Range: -4.8457

Max Act: 3.9852. Min Act: -0.0000

Data Index: 966976 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 4.8457. Min Range: -4.8457

Max Act: 3.9357. Min Act: -0.0000

Data Index: 1188726 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 4.8457. Min Range: -4.8457

Max Act: 3.9183. Min Act: -0.0000

Data Index: 330528 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 4.8457. Min Range: -4.8457

Max Act: 3.9341. Min Act: -0.0000

Data Index: 838557 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 4.8457. Min Range: -4.8457

Max Act: 3.9237. Min Act: -0.0000

Data Index: 693562 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 4.8457. Min Range: -4.8457

Max Act: 3.8884. Min Act: -0.0000

Data Index: 781262 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 4.8457. Min Range: -4.8457

Max Act: 3.8992. Min Act: -0.0000

Data Index: 153135 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 4.8457. Min Range: -4.8457

Max Act: 3.7061. Min Act: -0.0000

Data Index: 157088 (C4 (Web Text))

Max Activating Token Index: 355