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

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

Neuron 6116 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.2820. Min Act: -0.0000

Data Index: 1511870 (Python Code)

Max Activating Token Index: 234

Text #1

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.5565. Min Act: -0.0000

Data Index: 1643579 (Python Code)

Max Activating Token Index: 263

Text #2

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.2182. Min Act: -0.0000

Data Index: 1592053 (Python Code)

Max Activating Token Index: 86

Text #3

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.2972. Min Act: -0.0000

Data Index: 1504888 (Python Code)

Max Activating Token Index: 893

Text #4

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.0244. Min Act: -0.0000

Data Index: 1411973 (Python Code)

Max Activating Token Index: 384

Text #5

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.8227. Min Act: -0.0000

Data Index: 1593153 (Python Code)

Max Activating Token Index: 176

Text #6

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.8389. Min Act: -0.0000

Data Index: 208245 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.8579. Min Act: -0.0000

Data Index: 1627483 (Python Code)

Max Activating Token Index: 391

Text #8

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.9281. Min Act: -0.0000

Data Index: 1651778 (Python Code)

Max Activating Token Index: 210

Text #9

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.7380. Min Act: -0.0000

Data Index: 1486643 (Python Code)

Max Activating Token Index: 298

Text #10

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.7239. Min Act: -0.0000

Data Index: 1494799 (Python Code)

Max Activating Token Index: 475

Text #11

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.7855. Min Act: -0.0000

Data Index: 1559265 (Python Code)

Max Activating Token Index: 595

Text #12

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.7861. Min Act: -0.0000

Data Index: 1447791 (Python Code)

Max Activating Token Index: 331

Text #13

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.6562. Min Act: -0.0000

Data Index: 1396757 (Python Code)

Max Activating Token Index: 348

Text #14

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.6527. Min Act: -0.0000

Data Index: 1459342 (Python Code)

Max Activating Token Index: 384

Text #15

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.5615. Min Act: -0.0000

Data Index: 1384805 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.6447. Min Act: -0.0000

Data Index: 1475470 (Python Code)

Max Activating Token Index: 658

Text #17

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.6301. Min Act: -0.0000

Data Index: 1514022 (Python Code)

Max Activating Token Index: 441

Text #18

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.6267. Min Act: -0.0000

Data Index: 1481270 (Python Code)

Max Activating Token Index: 185

Text #19

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.6219. Min Act: -0.0000

Data Index: 1472645 (Python Code)

Max Activating Token Index: 564