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

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

Neuron 1460 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: 0.3873. Min Range: -0.3873

Max Act: 0.3873. Min Act: -0.0003

Data Index: 1068653 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3758. Min Act: -0.0003

Data Index: 1242886 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3570. Min Act: -0.0003

Data Index: 714455 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3623. Min Act: -0.0003

Data Index: 1112532 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3590. Min Act: -0.0003

Data Index: 1203281 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3373. Min Act: -0.0003

Data Index: 909113 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3341. Min Act: -0.0003

Data Index: 1135177 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3413. Min Act: -0.0003

Data Index: 346347 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3296. Min Act: -0.0003

Data Index: 1310829 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3391. Min Act: -0.0003

Data Index: 805862 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3387. Min Act: -0.0003

Data Index: 1124904 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3199. Min Act: -0.0003

Data Index: 444174 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3080. Min Act: -0.0003

Data Index: 454604 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3075. Min Act: -0.0003

Data Index: 822683 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2952. Min Act: -0.0003

Data Index: 1087074 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3032. Min Act: -0.0003

Data Index: 500013 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3032. Min Act: -0.0003

Data Index: 1173769 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3210. Min Act: -0.0003

Data Index: 1275703 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2828. Min Act: -0.0003

Data Index: 458846 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.3022. Min Act: -0.0003

Data Index: 473380 (C4 (Web Text))

Max Activating Token Index: 32