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

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

Neuron 714 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1199. Min Act: -0.0000

Data Index: 1502674 (Python Code)

Max Activating Token Index: 607

Text #1

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1594315 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1369954 (Python Code)

Max Activating Token Index: 925

Text #3

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1366022 (Python Code)

Max Activating Token Index: 269

Text #4

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0897. Min Act: -0.0000

Data Index: 1447905 (Python Code)

Max Activating Token Index: 337

Text #5

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1523438 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1552905 (Python Code)

Max Activating Token Index: 790

Text #7

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1566344 (Python Code)

Max Activating Token Index: 379

Text #8

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1439105 (Python Code)

Max Activating Token Index: 803

Text #9

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1168550 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1297564 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1437549 (Python Code)

Max Activating Token Index: 449

Text #12

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0836. Min Act: -0.0000

Data Index: 1606110 (Python Code)

Max Activating Token Index: 590

Text #13

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1560788 (Python Code)

Max Activating Token Index: 1015

Text #14

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1501417 (Python Code)

Max Activating Token Index: 722

Text #15

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1401048 (Python Code)

Max Activating Token Index: 160

Text #16

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0832. Min Act: -0.0000

Data Index: 661999 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0834. Min Act: -0.0000

Data Index: 310099 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1569475 (Python Code)

Max Activating Token Index: 461

Text #19

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1603336 (Python Code)

Max Activating Token Index: 656