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

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

Neuron 5083 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1386. Min Range: -4.1386

Max Act: 4.1386. Min Act: -0.0000

Data Index: 1468851 (Python Code)

Max Activating Token Index: 209

Text #1

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.8186. Min Act: 0.0000

Data Index: 690700 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.6539. Min Act: -0.0000

Data Index: 190746 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.4209. Min Act: 0.0000

Data Index: 841553 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.6804. Min Act: -0.0000

Data Index: 29235 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.4004. Min Act: -0.0000

Data Index: 348793 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.6817. Min Act: -0.0000

Data Index: 1003926 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.5410. Min Act: -0.0000

Data Index: 1150896 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.3601. Min Act: -0.0000

Data Index: 773225 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.3663. Min Act: 0.0000

Data Index: 685200 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.5166. Min Act: 0.0000

Data Index: 1033521 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.4872. Min Act: -0.0000

Data Index: 59339 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.3207. Min Act: -0.0000

Data Index: 965848 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.5571. Min Act: -0.0000

Data Index: 1611922 (Python Code)

Max Activating Token Index: 177

Text #14

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.3782. Min Act: -0.0000

Data Index: 1637365 (Python Code)

Max Activating Token Index: 161

Text #15

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.3615. Min Act: -0.0000

Data Index: 50461 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.2245. Min Act: -0.0000

Data Index: 1080919 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.3896. Min Act: -0.0000

Data Index: 506692 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.2052. Min Act: 0.0000

Data Index: 1409059 (Python Code)

Max Activating Token Index: 230

Text #19

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.2142. Min Act: -0.0000

Data Index: 824282 (C4 (Web Text))

Max Activating Token Index: 411