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

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

Neuron 1154 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1316171 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1446428 (Python Code)

Max Activating Token Index: 466

Text #2

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5985. Min Act: -0.0001

Data Index: 1378747 (Python Code)

Max Activating Token Index: 97

Text #3

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6006. Min Act: -0.0000

Data Index: 566966 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5929. Min Act: -0.0000

Data Index: 91005 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5749. Min Act: -0.0000

Data Index: 212231 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5436. Min Act: -0.0000

Data Index: 234611 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5620. Min Act: -0.0000

Data Index: 139791 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5426. Min Act: -0.0000

Data Index: 204808 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5205. Min Act: -0.0000

Data Index: 802724 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5635. Min Act: -0.0000

Data Index: 27134 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5122. Min Act: -0.0000

Data Index: 424208 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1005702 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5064. Min Act: -0.0000

Data Index: 344200 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1220988 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4797. Min Act: -0.0000

Data Index: 4391 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4938. Min Act: -0.0000

Data Index: 58827 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1650392 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4453. Min Act: -0.0000

Data Index: 467306 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4721. Min Act: -0.0000

Data Index: 784090 (C4 (Web Text))

Max Activating Token Index: 197