Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2896 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.7618. Min Act: -0.0001

Data Index: 1645817 (Python Code)

Max Activating Token Index: 25

Text #1

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.6324. Min Act: -0.0001

Data Index: 1534382 (Python Code)

Max Activating Token Index: 467

Text #2

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.4257. Min Act: -0.0001

Data Index: 641345 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.3115. Min Act: -0.0001

Data Index: 1487626 (Python Code)

Max Activating Token Index: 30

Text #4

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.3826. Min Act: -0.0001

Data Index: 101125 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.3604. Min Act: -0.0001

Data Index: 1224559 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.4028. Min Act: -0.0001

Data Index: 292111 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.4796. Min Act: -0.0001

Data Index: 125741 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.3269. Min Act: -0.0001

Data Index: 1593963 (Python Code)

Max Activating Token Index: 522

Text #9

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.3931. Min Act: -0.0001

Data Index: 1495049 (Python Code)

Max Activating Token Index: 262

Text #10

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.3181. Min Act: -0.0001

Data Index: 1279845 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.2139. Min Act: -0.0001

Data Index: 502074 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.3191. Min Act: -0.0001

Data Index: 1158159 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.1399. Min Act: -0.0001

Data Index: 1431171 (Python Code)

Max Activating Token Index: 731

Text #14

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.3066. Min Act: -0.0001

Data Index: 1091027 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.1704. Min Act: -0.0001

Data Index: 720380 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.2320. Min Act: -0.0001

Data Index: 1238455 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.3981. Min Act: -0.0001

Data Index: 1616120 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.3629. Min Act: -0.0001

Data Index: 1266792 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 1.7618. Min Range: -1.7618

Max Act: 1.2353. Min Act: -0.0001

Data Index: 201906 (C4 (Web Text))

Max Activating Token Index: 554