Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 738 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.8861. Min Act: -0.0000

Data Index: 1556163 (Python Code)

Max Activating Token Index: 316

Text #1

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.8556. Min Act: -0.0000

Data Index: 1633298 (Python Code)

Max Activating Token Index: 884

Text #2

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4886. Min Act: -0.0000

Data Index: 1479645 (Python Code)

Max Activating Token Index: 255

Text #3

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.6329. Min Act: -0.0001

Data Index: 1361220 (Python Code)

Max Activating Token Index: 171

Text #4

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.5678. Min Act: -0.0001

Data Index: 1656723 (Python Code)

Max Activating Token Index: 92

Text #5

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.5681. Min Act: -0.0000

Data Index: 1656425 (Python Code)

Max Activating Token Index: 648

Text #6

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4395. Min Act: -0.0000

Data Index: 1576292 (Python Code)

Max Activating Token Index: 834

Text #7

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4922. Min Act: -0.0001

Data Index: 1652674 (Python Code)

Max Activating Token Index: 792

Text #8

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4598. Min Act: -0.0000

Data Index: 1564384 (Python Code)

Max Activating Token Index: 1020

Text #9

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4577. Min Act: -0.0001

Data Index: 1542201 (Python Code)

Max Activating Token Index: 846

Text #10

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4057. Min Act: -0.0001

Data Index: 1452590 (Python Code)

Max Activating Token Index: 901

Text #11

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.5429. Min Act: -0.0000

Data Index: 1384819 (Python Code)

Max Activating Token Index: 862

Text #12

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4015. Min Act: -0.0001

Data Index: 1563090 (Python Code)

Max Activating Token Index: 283

Text #13

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.3574. Min Act: -0.0001

Data Index: 1600522 (Python Code)

Max Activating Token Index: 474

Text #14

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4017. Min Act: -0.0001

Data Index: 1586075 (Python Code)

Max Activating Token Index: 915

Text #15

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.3543. Min Act: -0.0000

Data Index: 1396939 (Python Code)

Max Activating Token Index: 788

Text #16

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.3796. Min Act: -0.0001

Data Index: 1638158 (Python Code)

Max Activating Token Index: 106

Text #17

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.3624. Min Act: -0.0000

Data Index: 1401050 (Python Code)

Max Activating Token Index: 557

Text #18

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4012. Min Act: -0.0001

Data Index: 1643344 (Python Code)

Max Activating Token Index: 68

Text #19

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.3932. Min Act: -0.0000

Data Index: 1424031 (Python Code)

Max Activating Token Index: 21