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

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

Neuron 5711 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: 1.9884. Min Range: -1.9884

Max Act: 1.9884. Min Act: -0.0000

Data Index: 1487069 (Python Code)

Max Activating Token Index: 994

Text #1

Max Range: 1.9884. Min Range: -1.9884

Max Act: 1.6350. Min Act: -0.0000

Data Index: 1519784 (Python Code)

Max Activating Token Index: 928

Text #2

Max Range: 1.9884. Min Range: -1.9884

Max Act: 1.3415. Min Act: -0.0000

Data Index: 1628651 (Python Code)

Max Activating Token Index: 643

Text #3

Max Range: 1.9884. Min Range: -1.9884

Max Act: 1.5089. Min Act: -0.0000

Data Index: 1638639 (Python Code)

Max Activating Token Index: 307

Text #4

Max Range: 1.9884. Min Range: -1.9884

Max Act: 1.4386. Min Act: -0.0000

Data Index: 1624063 (Python Code)

Max Activating Token Index: 457

Text #5

Max Range: 1.9884. Min Range: -1.9884

Max Act: 1.2563. Min Act: -0.0000

Data Index: 1536360 (Python Code)

Max Activating Token Index: 251

Text #6

Max Range: 1.9884. Min Range: -1.9884

Max Act: 1.2498. Min Act: -0.0000

Data Index: 1515293 (Python Code)

Max Activating Token Index: 603

Text #7

Max Range: 1.9884. Min Range: -1.9884

Max Act: 1.2076. Min Act: -0.0000

Data Index: 1402480 (Python Code)

Max Activating Token Index: 812

Text #8

Max Range: 1.9884. Min Range: -1.9884

Max Act: 1.1665. Min Act: -0.0000

Data Index: 1376575 (Python Code)

Max Activating Token Index: 263

Text #9

Max Range: 1.9884. Min Range: -1.9884

Max Act: 1.1421. Min Act: -0.0000

Data Index: 1490608 (Python Code)

Max Activating Token Index: 236

Text #10

Max Range: 1.9884. Min Range: -1.9884

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1575670 (Python Code)

Max Activating Token Index: 183

Text #11

Max Range: 1.9884. Min Range: -1.9884

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1581541 (Python Code)

Max Activating Token Index: 724

Text #12

Max Range: 1.9884. Min Range: -1.9884

Max Act: 1.0975. Min Act: -0.0000

Data Index: 1381604 (Python Code)

Max Activating Token Index: 901

Text #13

Max Range: 1.9884. Min Range: -1.9884

Max Act: 1.0718. Min Act: -0.0000

Data Index: 1565712 (Python Code)

Max Activating Token Index: 462

Text #14

Max Range: 1.9884. Min Range: -1.9884

Max Act: 1.0735. Min Act: -0.0000

Data Index: 556857 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 1.9884. Min Range: -1.9884

Max Act: 1.0823. Min Act: -0.0000

Data Index: 1396206 (Python Code)

Max Activating Token Index: 460

Text #16

Max Range: 1.9884. Min Range: -1.9884

Max Act: 0.8941. Min Act: -0.0000

Data Index: 1459634 (Python Code)

Max Activating Token Index: 142

Text #17

Max Range: 1.9884. Min Range: -1.9884

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1544333 (Python Code)

Max Activating Token Index: 954

Text #18

Max Range: 1.9884. Min Range: -1.9884

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1502088 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 1.9884. Min Range: -1.9884

Max Act: 0.8486. Min Act: -0.0000

Data Index: 1628153 (Python Code)

Max Activating Token Index: 828