Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2830 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5827. Min Act: -0.0001

Data Index: 1213152 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5727. Min Act: -0.0001

Data Index: 685752 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5556. Min Act: -0.0001

Data Index: 587715 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5461. Min Act: -0.0001

Data Index: 804814 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5431. Min Act: -0.0001

Data Index: 880750 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5629. Min Act: -0.0001

Data Index: 1096893 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5428. Min Act: -0.0001

Data Index: 267014 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5384. Min Act: -0.0001

Data Index: 71370 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5359. Min Act: -0.0001

Data Index: 521073 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4971. Min Act: -0.0001

Data Index: 300473 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4952. Min Act: -0.0001

Data Index: 257025 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5279. Min Act: -0.0001

Data Index: 432630 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4915. Min Act: -0.0001

Data Index: 204468 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5214. Min Act: -0.0001

Data Index: 231196 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5127. Min Act: -0.0001

Data Index: 465674 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5154. Min Act: -0.0001

Data Index: 100450 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5149. Min Act: -0.0001

Data Index: 28224 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4982. Min Act: -0.0001

Data Index: 1235479 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5278. Min Act: -0.0001

Data Index: 638222 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5115. Min Act: -0.0001

Data Index: 372063 (C4 (Web Text))

Max Activating Token Index: 549