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

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

Neuron 5327 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3295. Min Range: -2.3295

Max Act: 2.3295. Min Act: -0.0000

Data Index: 304661 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.6983. Min Act: -0.0000

Data Index: 54980 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.7110. Min Act: -0.0000

Data Index: 14842 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.7767. Min Act: -0.0000

Data Index: 1240678 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.6356. Min Act: -0.0000

Data Index: 230506 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.4240. Min Act: -0.0000

Data Index: 1656671 (Python Code)

Max Activating Token Index: 220

Text #6

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.5417. Min Act: -0.0000

Data Index: 1348936 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.4252. Min Act: -0.0000

Data Index: 27124 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.4302. Min Act: -0.0000

Data Index: 1240699 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.5050. Min Act: -0.0000

Data Index: 1546514 (Python Code)

Max Activating Token Index: 98

Text #10

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.3550. Min Act: -0.0000

Data Index: 667323 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.3297. Min Act: -0.0000

Data Index: 618466 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.3001. Min Act: -0.0000

Data Index: 1154612 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.2152. Min Act: -0.0000

Data Index: 912151 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.2258. Min Act: -0.0000

Data Index: 1607997 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.2258. Min Act: -0.0000

Data Index: 1585102 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1215149 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.2644. Min Act: -0.0000

Data Index: 1381518 (Python Code)

Max Activating Token Index: 465

Text #18

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.1832. Min Act: -0.0000

Data Index: 1390583 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 2.3295. Min Range: -2.3295

Max Act: 1.1058. Min Act: -0.0000

Data Index: 925752 (C4 (Web Text))

Max Activating Token Index: 330