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

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

Neuron 2831 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0261. Min Range: -2.0261

Max Act: 2.0261. Min Act: -0.0000

Data Index: 210634 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.8840. Min Act: -0.0000

Data Index: 226769 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.8664. Min Act: -0.0000

Data Index: 1228858 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.7431. Min Act: -0.0000

Data Index: 161940 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.6933. Min Act: -0.0000

Data Index: 455096 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.9320. Min Act: -0.0000

Data Index: 43141 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.6046. Min Act: -0.0000

Data Index: 500246 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1208474 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.5008. Min Act: -0.0000

Data Index: 459624 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.5200. Min Act: -0.0000

Data Index: 123011 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.5992. Min Act: -0.0000

Data Index: 1357427 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.6862. Min Act: -0.0000

Data Index: 232647 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.4873. Min Act: -0.0000

Data Index: 280366 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.4817. Min Act: -0.0000

Data Index: 1348441 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.4984. Min Act: -0.0000

Data Index: 261889 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.3834. Min Act: -0.0000

Data Index: 1334058 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.5333. Min Act: -0.0000

Data Index: 817185 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.7108. Min Act: -0.0000

Data Index: 730773 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.5349. Min Act: -0.0000

Data Index: 219607 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 2.0261. Min Range: -2.0261

Max Act: 1.4197. Min Act: -0.0000

Data Index: 70748 (C4 (Web Text))

Max Activating Token Index: 552