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

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

Neuron 2023 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: 4.2722. Min Range: -4.2722

Max Act: 4.2722. Min Act: -0.0000

Data Index: 975945 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 4.2722. Min Range: -4.2722

Max Act: 4.0605. Min Act: -0.0000

Data Index: 991609 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 4.2722. Min Range: -4.2722

Max Act: 3.6403. Min Act: -0.0000

Data Index: 1198104 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 4.2722. Min Range: -4.2722

Max Act: 3.2854. Min Act: -0.0000

Data Index: 228289 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.8290. Min Act: -0.0000

Data Index: 1110002 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.9614. Min Act: -0.0000

Data Index: 927691 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.6952. Min Act: -0.0000

Data Index: 793651 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.7534. Min Act: -0.0000

Data Index: 120554 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.8513. Min Act: -0.0000

Data Index: 664910 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.7146. Min Act: -0.0000

Data Index: 724306 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.7577. Min Act: -0.0000

Data Index: 1044854 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.2829. Min Act: -0.0000

Data Index: 1301985 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.6346. Min Act: -0.0000

Data Index: 102480 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.4832. Min Act: -0.0000

Data Index: 1301955 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.6181. Min Act: -0.0000

Data Index: 589079 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.2194. Min Act: -0.0000

Data Index: 595085 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.7246. Min Act: -0.0000

Data Index: 1298202 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.4527. Min Act: -0.0000

Data Index: 234557 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.3986. Min Act: -0.0000

Data Index: 1307193 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 4.2722. Min Range: -4.2722

Max Act: 2.3276. Min Act: -0.0000

Data Index: 1202298 (C4 (Web Text))

Max Activating Token Index: 601