Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 428 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.8168. Min Act: -0.0000

Data Index: 141636 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1145062 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7008. Min Act: -0.0000

Data Index: 736608 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6765. Min Act: -0.0000

Data Index: 513021 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7111. Min Act: -0.0000

Data Index: 795073 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1285307 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1048998 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5993. Min Act: -0.0000

Data Index: 704927 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5772. Min Act: -0.0000

Data Index: 966282 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1083814 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5530. Min Act: -0.0000

Data Index: 901518 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5677. Min Act: -0.0000

Data Index: 147918 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5395. Min Act: -0.0000

Data Index: 813934 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5380. Min Act: -0.0000

Data Index: 215339 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5105. Min Act: -0.0000

Data Index: 318798 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5054. Min Act: -0.0000

Data Index: 59793 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5193. Min Act: -0.0000

Data Index: 811593 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5216. Min Act: -0.0000

Data Index: 876503 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5201. Min Act: -0.0000

Data Index: 891255 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5508. Min Act: -0.0000

Data Index: 903557 (C4 (Web Text))

Max Activating Token Index: 311