Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 263 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1593466 (Python Code)

Max Activating Token Index: 288

Text #1

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1592954 (Python Code)

Max Activating Token Index: 724

Text #2

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.9285. Min Act: -0.0000

Data Index: 1620761 (Python Code)

Max Activating Token Index: 495

Text #3

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1605584 (Python Code)

Max Activating Token Index: 947

Text #4

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1385402 (Python Code)

Max Activating Token Index: 899

Text #5

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1639152 (Python Code)

Max Activating Token Index: 134

Text #6

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.9378. Min Act: -0.0000

Data Index: 1623536 (Python Code)

Max Activating Token Index: 314

Text #7

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8455. Min Act: -0.0000

Data Index: 1468552 (Python Code)

Max Activating Token Index: 972

Text #8

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1385477 (Python Code)

Max Activating Token Index: 384

Text #9

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1617814 (Python Code)

Max Activating Token Index: 739

Text #10

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1623936 (Python Code)

Max Activating Token Index: 753

Text #11

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7690. Min Act: -0.0000

Data Index: 1363248 (Python Code)

Max Activating Token Index: 355

Text #12

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1636025 (Python Code)

Max Activating Token Index: 492

Text #13

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1535441 (Python Code)

Max Activating Token Index: 208

Text #14

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1612381 (Python Code)

Max Activating Token Index: 750

Text #15

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7287. Min Act: -0.0000

Data Index: 1443319 (Python Code)

Max Activating Token Index: 581

Text #16

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1386945 (Python Code)

Max Activating Token Index: 126

Text #17

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1590553 (Python Code)

Max Activating Token Index: 365

Text #18

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1471965 (Python Code)

Max Activating Token Index: 461

Text #19

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1646016 (Python Code)

Max Activating Token Index: 749