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

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

Neuron 6125 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4287. Min Range: -2.4287

Max Act: 2.4287. Min Act: -0.0000

Data Index: 351341 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 2.4287. Min Range: -2.4287

Max Act: 2.2899. Min Act: -0.0000

Data Index: 873342 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.9616. Min Act: -0.0000

Data Index: 28868 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.9898. Min Act: -0.0001

Data Index: 180532 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.8512. Min Act: -0.0000

Data Index: 528820 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.9373. Min Act: -0.0001

Data Index: 1091598 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.9030. Min Act: -0.0000

Data Index: 706580 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.8034. Min Act: -0.0000

Data Index: 546537 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.5717. Min Act: -0.0001

Data Index: 296272 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.6159. Min Act: -0.0000

Data Index: 324542 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.7686. Min Act: -0.0000

Data Index: 605409 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.7589. Min Act: -0.0001

Data Index: 1210241 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.5128. Min Act: -0.0000

Data Index: 1294795 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.7088. Min Act: -0.0001

Data Index: 974813 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.6253. Min Act: -0.0000

Data Index: 934951 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.6802. Min Act: -0.0000

Data Index: 359949 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.6681. Min Act: -0.0001

Data Index: 1284184 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.6458. Min Act: -0.0000

Data Index: 985662 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.4239. Min Act: -0.0000

Data Index: 327896 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 2.4287. Min Range: -2.4287

Max Act: 1.6105. Min Act: -0.0001

Data Index: 1263533 (C4 (Web Text))

Max Activating Token Index: 317