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

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

Neuron 6132 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.5133. Min Act: -0.0000

Data Index: 624210 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.4296. Min Act: -0.0000

Data Index: 184636 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.4199. Min Act: 0.0000

Data Index: 718327 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1270890 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1134683 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1049830 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.4169. Min Act: -0.0000

Data Index: 667759 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3864. Min Act: -0.0000

Data Index: 346368 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3815. Min Act: -0.0000

Data Index: 99395 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1166623 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3929. Min Act: -0.0000

Data Index: 420976 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.4133. Min Act: -0.0000

Data Index: 120096 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3771. Min Act: 0.0000

Data Index: 449713 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3743. Min Act: -0.0000

Data Index: 379677 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3750. Min Act: -0.0000

Data Index: 893628 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3743. Min Act: -0.0000

Data Index: 910019 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3817. Min Act: -0.0000

Data Index: 30088 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1218394 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1109462 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3580. Min Act: -0.0000

Data Index: 170160 (C4 (Web Text))

Max Activating Token Index: 258