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

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

Neuron 2051 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3768. Min Range: -1.3768

Max Act: 1.2191. Min Act: -0.0000

Data Index: 323073 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 1.3768. Min Range: -1.3768

Max Act: 1.2857. Min Act: -0.0000

Data Index: 1119312 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 1.3768. Min Range: -1.3768

Max Act: 1.3768. Min Act: -0.0000

Data Index: 437495 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 1.3768. Min Range: -1.3768

Max Act: 1.2208. Min Act: -0.0000

Data Index: 82906 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 1.3768. Min Range: -1.3768

Max Act: 1.1945. Min Act: -0.0000

Data Index: 431817 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 1.3768. Min Range: -1.3768

Max Act: 1.1116. Min Act: 0.0000

Data Index: 120938 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 1.3768. Min Range: -1.3768

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1212243 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 1.3768. Min Range: -1.3768

Max Act: 1.1919. Min Act: -0.0000

Data Index: 493946 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 1.3768. Min Range: -1.3768

Max Act: 1.1062. Min Act: -0.0000

Data Index: 550276 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 1.3768. Min Range: -1.3768

Max Act: 1.0614. Min Act: -0.0000

Data Index: 1512965 (Python Code)

Max Activating Token Index: 42

Text #10

Max Range: 1.3768. Min Range: -1.3768

Max Act: 1.0823. Min Act: 0.0000

Data Index: 289030 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 1.3768. Min Range: -1.3768

Max Act: 1.1271. Min Act: -0.0000

Data Index: 491525 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 1.3768. Min Range: -1.3768

Max Act: 0.9755. Min Act: -0.0000

Data Index: 1308263 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 1.3768. Min Range: -1.3768

Max Act: 1.0256. Min Act: -0.0000

Data Index: 92394 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 1.3768. Min Range: -1.3768

Max Act: 1.0050. Min Act: -0.0000

Data Index: 1586397 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 1.3768. Min Range: -1.3768

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1459519 (Python Code)

Max Activating Token Index: 177

Text #16

Max Range: 1.3768. Min Range: -1.3768

Max Act: 1.0188. Min Act: -0.0000

Data Index: 542945 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 1.3768. Min Range: -1.3768

Max Act: 0.9669. Min Act: -0.0000

Data Index: 586625 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 1.3768. Min Range: -1.3768

Max Act: 0.9283. Min Act: -0.0000

Data Index: 737335 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 1.3768. Min Range: -1.3768

Max Act: 0.9409. Min Act: -0.0000

Data Index: 1309486 (C4 (Web Text))

Max Activating Token Index: 165