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

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

Neuron 2754 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0253. Min Range: -1.0253

Max Act: 1.0253. Min Act: -0.0001

Data Index: 727354 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.8194. Min Act: -0.0000

Data Index: 687998 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.6100. Min Act: -0.0001

Data Index: 68329 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7400. Min Act: -0.0001

Data Index: 1211303 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.6218. Min Act: -0.0001

Data Index: 321366 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7155. Min Act: -0.0001

Data Index: 1003289 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.4300. Min Act: -0.0001

Data Index: 774486 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7836. Min Act: -0.0001

Data Index: 987688 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1279320 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.5270. Min Act: -0.0001

Data Index: 645281 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.2468. Min Act: -0.0001

Data Index: 446402 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.5245. Min Act: -0.0001

Data Index: 820720 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.4272. Min Act: -0.0000

Data Index: 618694 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.5796. Min Act: -0.0000

Data Index: 310441 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.5841. Min Act: -0.0001

Data Index: 856163 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1162680 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.4722. Min Act: -0.0001

Data Index: 114392 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.3535. Min Act: -0.0000

Data Index: 296799 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.3317. Min Act: -0.0001

Data Index: 884480 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.2927. Min Act: -0.0000

Data Index: 84515 (C4 (Web Text))

Max Activating Token Index: 671