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

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

Neuron 2628 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3438. Min Act: -0.0000

Data Index: 472747 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1062930 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3722. Min Act: -0.0001

Data Index: 784136 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3670. Min Act: -0.0001

Data Index: 728836 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3317. Min Act: -0.0001

Data Index: 926742 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3566. Min Act: -0.0000

Data Index: 442051 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3141. Min Act: -0.0000

Data Index: 493266 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3307. Min Act: -0.0001

Data Index: 1082003 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3215. Min Act: -0.0000

Data Index: 913411 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3168. Min Act: -0.0001

Data Index: 208274 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3208. Min Act: -0.0000

Data Index: 248010 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3133. Min Act: -0.0000

Data Index: 550639 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3391. Min Act: -0.0000

Data Index: 197396 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.2929. Min Act: -0.0001

Data Index: 749183 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.2788. Min Act: -0.0001

Data Index: 688223 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.2783. Min Act: -0.0001

Data Index: 1289749 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.2651. Min Act: -0.0000

Data Index: 385825 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3130. Min Act: -0.0000

Data Index: 18282 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.2798. Min Act: -0.0000

Data Index: 862554 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.2834. Min Act: -0.0001

Data Index: 1011626 (C4 (Web Text))

Max Activating Token Index: 238