Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 388 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2201. Min Act: -0.0003

Data Index: 1146123 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1994. Min Act: -0.0003

Data Index: 987739 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1819. Min Act: -0.0003

Data Index: 1206081 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1879. Min Act: -0.0003

Data Index: 994800 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1541. Min Act: -0.0003

Data Index: 861235 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1793. Min Act: -0.0003

Data Index: 31871 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1770. Min Act: -0.0003

Data Index: 559083 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1731. Min Act: -0.0003

Data Index: 591538 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1706. Min Act: -0.0003

Data Index: 1319319 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1523. Min Act: -0.0003

Data Index: 410245 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1499. Min Act: -0.0003

Data Index: 339118 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1475. Min Act: -0.0003

Data Index: 140364 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1448. Min Act: -0.0003

Data Index: 797329 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1211. Min Act: -0.0003

Data Index: 670066 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1632. Min Act: -0.0003

Data Index: 475026 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1507. Min Act: -0.0003

Data Index: 172312 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1280. Min Act: -0.0003

Data Index: 1214053 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1429. Min Act: -0.0003

Data Index: 693791 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1463. Min Act: -0.0003

Data Index: 829500 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1654. Min Act: -0.0003

Data Index: 7028 (C4 (Web Text))

Max Activating Token Index: 580