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

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

Neuron 2060 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.5379. Min Act: -0.0000

Data Index: 509692 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.2834. Min Act: -0.0000

Data Index: 1109990 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.6597. Min Act: -0.0000

Data Index: 584447 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.7663. Min Act: -0.0000

Data Index: 1049212 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.3504. Min Act: -0.0000

Data Index: 1250899 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.4564. Min Act: -0.0000

Data Index: 841149 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.4435. Min Act: -0.0000

Data Index: 55078 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.5611. Min Act: -0.0000

Data Index: 1319837 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.5518. Min Act: -0.0000

Data Index: 1324083 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.3882. Min Act: -0.0000

Data Index: 1444871 (Python Code)

Max Activating Token Index: 559

Text #10

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.3484. Min Act: -0.0000

Data Index: 367808 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.3132. Min Act: -0.0000

Data Index: 454532 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.4135. Min Act: -0.0000

Data Index: 1490120 (Python Code)

Max Activating Token Index: 61

Text #13

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.1674. Min Act: -0.0000

Data Index: 955146 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.2778. Min Act: -0.0000

Data Index: 145465 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.2429. Min Act: -0.0000

Data Index: 1105222 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.2203. Min Act: -0.0000

Data Index: 1318755 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.2284. Min Act: -0.0000

Data Index: 1166449 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.3355. Min Act: -0.0000

Data Index: 179220 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 2.7663. Min Range: -2.7663

Max Act: 2.3213. Min Act: -0.0000

Data Index: 1132683 (C4 (Web Text))

Max Activating Token Index: 377