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

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

Neuron 3709 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.4224. Min Act: -0.0001

Data Index: 1221042 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.4518. Min Act: -0.0000

Data Index: 740160 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.2986. Min Act: -0.0000

Data Index: 156207 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.3830. Min Act: -0.0000

Data Index: 431871 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.2874. Min Act: -0.0001

Data Index: 32685 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.2671. Min Act: -0.0000

Data Index: 541879 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.2458. Min Act: -0.0000

Data Index: 868506 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.2269. Min Act: -0.0001

Data Index: 213200 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.2333. Min Act: -0.0000

Data Index: 444052 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.2915. Min Act: -0.0001

Data Index: 911086 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.2232. Min Act: -0.0000

Data Index: 580858 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.2157. Min Act: -0.0000

Data Index: 147121 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.2098. Min Act: -0.0000

Data Index: 1263033 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.1044. Min Act: -0.0000

Data Index: 489033 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.1292. Min Act: -0.0000

Data Index: 592785 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.1614. Min Act: -0.0000

Data Index: 52112 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.1814. Min Act: -0.0000

Data Index: 1102932 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.2167. Min Act: -0.0000

Data Index: 1172692 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.2375. Min Act: -0.0000

Data Index: 1350690 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.1653. Min Act: -0.0000

Data Index: 733968 (C4 (Web Text))

Max Activating Token Index: 444