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

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

Neuron 856 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: 1.8865. Min Range: -1.8865

Max Act: 1.8865. Min Act: -0.0000

Data Index: 1539079 (Python Code)

Max Activating Token Index: 1010

Text #1

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.8664. Min Act: -0.0000

Data Index: 1492722 (Python Code)

Max Activating Token Index: 946

Text #2

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.8428. Min Act: -0.0000

Data Index: 1452843 (Python Code)

Max Activating Token Index: 132

Text #3

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.8339. Min Act: -0.0000

Data Index: 1577966 (Python Code)

Max Activating Token Index: 74

Text #4

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.7529. Min Act: -0.0000

Data Index: 93987 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6458. Min Act: -0.0000

Data Index: 833241 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6002. Min Act: -0.0000

Data Index: 1543010 (Python Code)

Max Activating Token Index: 559

Text #7

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6234. Min Act: -0.0000

Data Index: 1557953 (Python Code)

Max Activating Token Index: 37

Text #8

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6589. Min Act: -0.0000

Data Index: 976625 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6139. Min Act: -0.0000

Data Index: 1400434 (Python Code)

Max Activating Token Index: 602

Text #10

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.6099. Min Act: -0.0000

Data Index: 1450080 (Python Code)

Max Activating Token Index: 723

Text #11

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.5885. Min Act: -0.0000

Data Index: 538044 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.5112. Min Act: -0.0000

Data Index: 576174 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.5734. Min Act: -0.0000

Data Index: 640099 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.5621. Min Act: -0.0000

Data Index: 1651031 (Python Code)

Max Activating Token Index: 450

Text #15

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.5429. Min Act: -0.0000

Data Index: 300730 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.4890. Min Act: -0.0000

Data Index: 1376004 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.4479. Min Act: -0.0000

Data Index: 623435 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.5721. Min Act: -0.0000

Data Index: 1438679 (Python Code)

Max Activating Token Index: 557

Text #19

Max Range: 1.8865. Min Range: -1.8865

Max Act: 1.5233. Min Act: -0.0000

Data Index: 1273283 (C4 (Web Text))

Max Activating Token Index: 105