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

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

Neuron 2433 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7874. Min Range: -2.7874

Max Act: 2.7874. Min Act: -0.0000

Data Index: 710580 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 2.7874. Min Range: -2.7874

Max Act: 2.7389. Min Act: -0.0000

Data Index: 1190876 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 2.7874. Min Range: -2.7874

Max Act: 2.2707. Min Act: -0.0000

Data Index: 281369 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 2.7874. Min Range: -2.7874

Max Act: 2.2867. Min Act: -0.0000

Data Index: 278368 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 2.7874. Min Range: -2.7874

Max Act: 2.1424. Min Act: -0.0000

Data Index: 1064853 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 2.7874. Min Range: -2.7874

Max Act: 2.3935. Min Act: -0.0000

Data Index: 398720 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 2.7874. Min Range: -2.7874

Max Act: 2.2376. Min Act: -0.0000

Data Index: 445309 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 2.7874. Min Range: -2.7874

Max Act: 2.2772. Min Act: -0.0000

Data Index: 721508 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 2.7874. Min Range: -2.7874

Max Act: 2.1273. Min Act: -0.0000

Data Index: 1114818 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 2.7874. Min Range: -2.7874

Max Act: 1.6209. Min Act: -0.0000

Data Index: 1381804 (Python Code)

Max Activating Token Index: 881

Text #10

Max Range: 2.7874. Min Range: -2.7874

Max Act: 1.8142. Min Act: -0.0000

Data Index: 580216 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 2.7874. Min Range: -2.7874

Max Act: 1.9309. Min Act: -0.0000

Data Index: 1342783 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 2.7874. Min Range: -2.7874

Max Act: 2.0222. Min Act: -0.0000

Data Index: 1457425 (Python Code)

Max Activating Token Index: 854

Text #13

Max Range: 2.7874. Min Range: -2.7874

Max Act: 2.1232. Min Act: -0.0000

Data Index: 128073 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 2.7874. Min Range: -2.7874

Max Act: 2.0083. Min Act: -0.0000

Data Index: 1647420 (Python Code)

Max Activating Token Index: 752

Text #15

Max Range: 2.7874. Min Range: -2.7874

Max Act: 1.8851. Min Act: -0.0000

Data Index: 1548546 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 2.7874. Min Range: -2.7874

Max Act: 2.1062. Min Act: -0.0000

Data Index: 1514031 (Python Code)

Max Activating Token Index: 61

Text #17

Max Range: 2.7874. Min Range: -2.7874

Max Act: 1.9916. Min Act: -0.0000

Data Index: 1478652 (Python Code)

Max Activating Token Index: 50

Text #18

Max Range: 2.7874. Min Range: -2.7874

Max Act: 1.9924. Min Act: -0.0000

Data Index: 1505051 (Python Code)

Max Activating Token Index: 721

Text #19

Max Range: 2.7874. Min Range: -2.7874

Max Act: 1.7419. Min Act: -0.0000

Data Index: 1595130 (Python Code)

Max Activating Token Index: 969