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

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

Neuron 3438 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: 1.5301. Min Range: -1.5301

Max Act: 1.5301. Min Act: -0.0000

Data Index: 932862 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.4543. Min Act: -0.0000

Data Index: 816305 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.4338. Min Act: -0.0000

Data Index: 1137116 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.4067. Min Act: -0.0000

Data Index: 591270 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.2674. Min Act: 0.0000

Data Index: 1040717 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.2615. Min Act: -0.0000

Data Index: 843790 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.2530. Min Act: -0.0000

Data Index: 270583 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.1535. Min Act: 0.0001

Data Index: 1354455 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.2137. Min Act: -0.0000

Data Index: 140579 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.2005. Min Act: 0.0001

Data Index: 277680 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.2409. Min Act: -0.0000

Data Index: 950865 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.2195. Min Act: -0.0000

Data Index: 988118 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.1469. Min Act: -0.0000

Data Index: 13636 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.0745. Min Act: -0.0000

Data Index: 167186 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.1390. Min Act: -0.0000

Data Index: 315501 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.1391. Min Act: -0.0000

Data Index: 846404 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.2039. Min Act: 0.0001

Data Index: 76079 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.1151. Min Act: -0.0000

Data Index: 1108471 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.1080. Min Act: -0.0000

Data Index: 326927 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 1.5301. Min Range: -1.5301

Max Act: 1.0983. Min Act: -0.0000

Data Index: 631075 (C4 (Web Text))

Max Activating Token Index: 278