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

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

Neuron 555 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1650260 (Python Code)

Max Activating Token Index: 772

Text #1

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1410289 (Python Code)

Max Activating Token Index: 720

Text #2

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1432532 (Python Code)

Max Activating Token Index: 955

Text #3

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3236. Min Act: -0.0000

Data Index: 1610551 (Python Code)

Max Activating Token Index: 865

Text #4

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1575461 (Python Code)

Max Activating Token Index: 43

Text #5

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3210. Min Act: -0.0000

Data Index: 1559698 (Python Code)

Max Activating Token Index: 504

Text #6

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1549984 (Python Code)

Max Activating Token Index: 739

Text #7

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1393311 (Python Code)

Max Activating Token Index: 954

Text #8

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1572176 (Python Code)

Max Activating Token Index: 328

Text #9

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3072. Min Act: -0.0000

Data Index: 1494763 (Python Code)

Max Activating Token Index: 53

Text #10

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1406975 (Python Code)

Max Activating Token Index: 269

Text #11

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2792. Min Act: -0.0000

Data Index: 1621042 (Python Code)

Max Activating Token Index: 201

Text #12

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1468113 (Python Code)

Max Activating Token Index: 929

Text #13

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2839. Min Act: -0.0000

Data Index: 1444398 (Python Code)

Max Activating Token Index: 633

Text #14

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1451622 (Python Code)

Max Activating Token Index: 144

Text #15

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2821. Min Act: -0.0000

Data Index: 290782 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1496085 (Python Code)

Max Activating Token Index: 318

Text #17

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1326382 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1439892 (Python Code)

Max Activating Token Index: 834

Text #19

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1446091 (Python Code)

Max Activating Token Index: 628