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

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

Neuron 679 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9847. Min Range: -2.9847

Max Act: 2.9847. Min Act: -0.0000

Data Index: 1201105 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 2.9847. Min Range: -2.9847

Max Act: 2.3000. Min Act: -0.0000

Data Index: 820848 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 2.9847. Min Range: -2.9847

Max Act: 2.3261. Min Act: -0.0000

Data Index: 167202 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 2.9847. Min Range: -2.9847

Max Act: 2.1132. Min Act: -0.0000

Data Index: 878111 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.8602. Min Act: -0.0000

Data Index: 1048134 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.7389. Min Act: -0.0001

Data Index: 272323 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.8212. Min Act: -0.0000

Data Index: 1003321 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.8128. Min Act: -0.0000

Data Index: 310952 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.6934. Min Act: -0.0000

Data Index: 671308 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.6576. Min Act: -0.0000

Data Index: 1016023 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.8459. Min Act: -0.0000

Data Index: 723250 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.7187. Min Act: -0.0000

Data Index: 109706 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.7052. Min Act: -0.0000

Data Index: 1327750 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.7892. Min Act: -0.0000

Data Index: 397022 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.7812. Min Act: -0.0000

Data Index: 15211 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.7594. Min Act: -0.0000

Data Index: 981978 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.6704. Min Act: -0.0000

Data Index: 18752 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.6614. Min Act: -0.0001

Data Index: 430977 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.4677. Min Act: -0.0000

Data Index: 1306861 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 2.9847. Min Range: -2.9847

Max Act: 1.5311. Min Act: -0.0000

Data Index: 582837 (C4 (Web Text))

Max Activating Token Index: 208