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

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

Neuron 192 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: 2.1128. Min Range: -2.1128

Max Act: 2.1128. Min Act: -0.0000

Data Index: 842593 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.7578. Min Act: -0.0000

Data Index: 1064765 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.6583. Min Act: -0.0000

Data Index: 212601 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.6318. Min Act: -0.0000

Data Index: 369058 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.7112. Min Act: -0.0000

Data Index: 358866 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.5248. Min Act: -0.0000

Data Index: 1450024 (Python Code)

Max Activating Token Index: 282

Text #6

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.5663. Min Act: -0.0000

Data Index: 1054477 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.5452. Min Act: -0.0000

Data Index: 476986 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.5735. Min Act: -0.0000

Data Index: 237332 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.4970. Min Act: -0.0000

Data Index: 131039 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.4486. Min Act: -0.0000

Data Index: 258459 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.4600. Min Act: -0.0000

Data Index: 1131798 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.4373. Min Act: -0.0000

Data Index: 189334 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.3941. Min Act: -0.0000

Data Index: 161904 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.3955. Min Act: -0.0000

Data Index: 758276 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.3894. Min Act: -0.0000

Data Index: 547021 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.3807. Min Act: -0.0000

Data Index: 536307 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.4126. Min Act: -0.0000

Data Index: 130493 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.4395. Min Act: -0.0000

Data Index: 329170 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 2.1128. Min Range: -2.1128

Max Act: 1.3530. Min Act: -0.0000

Data Index: 1096638 (C4 (Web Text))

Max Activating Token Index: 68