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

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

Neuron 5602 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.7197. Min Act: -0.0000

Data Index: 312898 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.4143. Min Act: -0.0000

Data Index: 294102 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.1852. Min Act: -0.0000

Data Index: 713820 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.0353. Min Act: -0.0000

Data Index: 816315 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.8437. Min Act: -0.0000

Data Index: 515666 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.6452. Min Act: -0.0000

Data Index: 762811 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.8273. Min Act: -0.0000

Data Index: 1011242 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.8138. Min Act: -0.0000

Data Index: 918989 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.8252. Min Act: -0.0000

Data Index: 1012562 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.7695. Min Act: -0.0000

Data Index: 735352 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.1991. Min Act: -0.0000

Data Index: 1253551 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.5457. Min Act: -0.0000

Data Index: 653015 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.7507. Min Act: -0.0000

Data Index: 1532168 (Python Code)

Max Activating Token Index: 642

Text #13

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.6300. Min Act: -0.0000

Data Index: 861657 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.6365. Min Act: -0.0000

Data Index: 699709 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.8448. Min Act: -0.0000

Data Index: 1033397 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.5250. Min Act: -0.0000

Data Index: 492943 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.7384. Min Act: -0.0000

Data Index: 735247 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.6035. Min Act: -0.0000

Data Index: 746263 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.5620. Min Act: -0.0000

Data Index: 61425 (C4 (Web Text))

Max Activating Token Index: 916