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

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

Neuron 99 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2585. Min Act: -0.0001

Data Index: 636145 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2247. Min Act: -0.0001

Data Index: 1329463 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2006. Min Act: -0.0001

Data Index: 502073 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1615. Min Act: -0.0001

Data Index: 391596 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2535. Min Act: -0.0001

Data Index: 448358 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1761. Min Act: -0.0001

Data Index: 690265 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2243. Min Act: -0.0001

Data Index: 813863 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2087. Min Act: -0.0001

Data Index: 93513 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2324. Min Act: -0.0001

Data Index: 746695 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1782. Min Act: -0.0001

Data Index: 964915 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1625. Min Act: -0.0001

Data Index: 1261268 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1314. Min Act: -0.0001

Data Index: 773841 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1856. Min Act: -0.0001

Data Index: 1211560 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1338444 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1055872 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1761. Min Act: -0.0001

Data Index: 895574 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1550. Min Act: -0.0001

Data Index: 1259849 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1994. Min Act: -0.0001

Data Index: 1049010 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1815. Min Act: -0.0001

Data Index: 1531865 (Python Code)

Max Activating Token Index: 795

Text #19

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1201593 (C4 (Web Text))

Max Activating Token Index: 623