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

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

Neuron 2027 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: 2.5981. Min Range: -2.5981

Max Act: 2.5981. Min Act: -0.0000

Data Index: 1599666 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 2.5981. Min Range: -2.5981

Max Act: 2.5362. Min Act: -0.0000

Data Index: 1417633 (Python Code)

Max Activating Token Index: 174

Text #2

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.9909. Min Act: -0.0000

Data Index: 1491749 (Python Code)

Max Activating Token Index: 810

Text #3

Max Range: 2.5981. Min Range: -2.5981

Max Act: 2.0246. Min Act: -0.0000

Data Index: 1453480 (Python Code)

Max Activating Token Index: 818

Text #4

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.8814. Min Act: -0.0000

Data Index: 1498406 (Python Code)

Max Activating Token Index: 187

Text #5

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.8299. Min Act: -0.0000

Data Index: 1509569 (Python Code)

Max Activating Token Index: 150

Text #6

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.7278. Min Act: -0.0000

Data Index: 1157659 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.7376. Min Act: -0.0000

Data Index: 1529381 (Python Code)

Max Activating Token Index: 173

Text #8

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.8456. Min Act: -0.0000

Data Index: 314841 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.5697. Min Act: -0.0000

Data Index: 1554397 (Python Code)

Max Activating Token Index: 514

Text #10

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.8178. Min Act: -0.0000

Data Index: 1235561 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.5128. Min Act: -0.0000

Data Index: 141770 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.4499. Min Act: -0.0000

Data Index: 1582771 (Python Code)

Max Activating Token Index: 890

Text #13

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.5330. Min Act: -0.0000

Data Index: 1400484 (Python Code)

Max Activating Token Index: 593

Text #14

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.5047. Min Act: -0.0000

Data Index: 669062 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.5808. Min Act: -0.0000

Data Index: 1612010 (Python Code)

Max Activating Token Index: 937

Text #16

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.2919. Min Act: -0.0000

Data Index: 1626540 (Python Code)

Max Activating Token Index: 322

Text #17

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.5310. Min Act: -0.0000

Data Index: 1337307 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.4958. Min Act: -0.0000

Data Index: 1468134 (Python Code)

Max Activating Token Index: 337

Text #19

Max Range: 2.5981. Min Range: -2.5981

Max Act: 1.5295. Min Act: -0.0000

Data Index: 1617460 (Python Code)

Max Activating Token Index: 61