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

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

Neuron 6139 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6399. Min Range: -4.6399

Max Act: 4.6255. Min Act: -0.0000

Data Index: 224306 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 4.6399. Min Range: -4.6399

Max Act: 4.6399. Min Act: -0.0000

Data Index: 1257744 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 4.6399. Min Range: -4.6399

Max Act: 4.4388. Min Act: -0.0000

Data Index: 377269 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 4.6399. Min Range: -4.6399

Max Act: 4.2966. Min Act: -0.0000

Data Index: 1055078 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 4.6399. Min Range: -4.6399

Max Act: 4.1961. Min Act: -0.0000

Data Index: 1045089 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 4.6399. Min Range: -4.6399

Max Act: 4.2249. Min Act: -0.0000

Data Index: 257092 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 4.6399. Min Range: -4.6399

Max Act: 3.9224. Min Act: -0.0000

Data Index: 314714 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 4.6399. Min Range: -4.6399

Max Act: 3.5370. Min Act: -0.0000

Data Index: 711705 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 4.6399. Min Range: -4.6399

Max Act: 3.6720. Min Act: -0.0000

Data Index: 353170 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 4.6399. Min Range: -4.6399

Max Act: 3.6576. Min Act: -0.0000

Data Index: 1357713 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 4.6399. Min Range: -4.6399

Max Act: 3.6458. Min Act: -0.0000

Data Index: 458653 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 4.6399. Min Range: -4.6399

Max Act: 3.5971. Min Act: -0.0000

Data Index: 827910 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 4.6399. Min Range: -4.6399

Max Act: 3.4069. Min Act: -0.0000

Data Index: 533957 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 4.6399. Min Range: -4.6399

Max Act: 3.4824. Min Act: -0.0000

Data Index: 1352526 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 4.6399. Min Range: -4.6399

Max Act: 3.4624. Min Act: -0.0000

Data Index: 138520 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 4.6399. Min Range: -4.6399

Max Act: 3.3759. Min Act: -0.0000

Data Index: 1125119 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 4.6399. Min Range: -4.6399

Max Act: 3.3528. Min Act: -0.0000

Data Index: 672671 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 4.6399. Min Range: -4.6399

Max Act: 3.3447. Min Act: -0.0000

Data Index: 499664 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 4.6399. Min Range: -4.6399

Max Act: 3.3497. Min Act: -0.0000

Data Index: 809746 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 4.6399. Min Range: -4.6399

Max Act: 3.3408. Min Act: -0.0000

Data Index: 1189823 (C4 (Web Text))

Max Activating Token Index: 603