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

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

Neuron 4092 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: 4.1259. Min Range: -4.1259

Max Act: 4.1259. Min Act: -0.0000

Data Index: 1349479 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 4.1259. Min Range: -4.1259

Max Act: 3.9823. Min Act: -0.0000

Data Index: 21656 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 4.1259. Min Range: -4.1259

Max Act: 3.6919. Min Act: -0.0000

Data Index: 1154006 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 4.1259. Min Range: -4.1259

Max Act: 3.3989. Min Act: -0.0000

Data Index: 1290035 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 4.1259. Min Range: -4.1259

Max Act: 3.2818. Min Act: -0.0000

Data Index: 378871 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 4.1259. Min Range: -4.1259

Max Act: 2.8994. Min Act: -0.0001

Data Index: 53523 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 4.1259. Min Range: -4.1259

Max Act: 3.1861. Min Act: -0.0000

Data Index: 430541 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 4.1259. Min Range: -4.1259

Max Act: 2.9272. Min Act: -0.0000

Data Index: 960472 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 4.1259. Min Range: -4.1259

Max Act: 2.9156. Min Act: -0.0000

Data Index: 1284794 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 4.1259. Min Range: -4.1259

Max Act: 2.4531. Min Act: -0.0000

Data Index: 329683 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 4.1259. Min Range: -4.1259

Max Act: 2.6543. Min Act: -0.0000

Data Index: 467585 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 4.1259. Min Range: -4.1259

Max Act: 2.6063. Min Act: -0.0000

Data Index: 1358321 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 4.1259. Min Range: -4.1259

Max Act: 2.6987. Min Act: -0.0000

Data Index: 380103 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 4.1259. Min Range: -4.1259

Max Act: 2.5574. Min Act: -0.0000

Data Index: 573907 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 4.1259. Min Range: -4.1259

Max Act: 2.4888. Min Act: -0.0000

Data Index: 1333076 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 4.1259. Min Range: -4.1259

Max Act: 2.3194. Min Act: -0.0000

Data Index: 873842 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 4.1259. Min Range: -4.1259

Max Act: 2.3241. Min Act: -0.0000

Data Index: 285100 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 4.1259. Min Range: -4.1259

Max Act: 2.3228. Min Act: -0.0000

Data Index: 292906 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 4.1259. Min Range: -4.1259

Max Act: 2.3974. Min Act: -0.0000

Data Index: 854471 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 4.1259. Min Range: -4.1259

Max Act: 2.4882. Min Act: -0.0000

Data Index: 741271 (C4 (Web Text))

Max Activating Token Index: 176