Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 682 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1074181 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0537. Min Act: -0.0002

Data Index: 532850 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0522. Min Act: -0.0002

Data Index: 446937 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0505. Min Act: -0.0002

Data Index: 60924 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0507. Min Act: -0.0002

Data Index: 507786 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0489. Min Act: -0.0002

Data Index: 210312 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1281727 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0498. Min Act: -0.0002

Data Index: 233407 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1259826 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1251327 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0476. Min Act: -0.0002

Data Index: 546504 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1160033 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0476. Min Act: -0.0002

Data Index: 987217 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1579027 (Python Code)

Max Activating Token Index: 158

Text #14

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1123338 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0446. Min Act: -0.0002

Data Index: 995864 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0478. Min Act: -0.0002

Data Index: 977049 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0460. Min Act: -0.0002

Data Index: 19124 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0455. Min Act: -0.0002

Data Index: 560668 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1080283 (C4 (Web Text))

Max Activating Token Index: 246