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

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

Neuron 696 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: 1.1846. Min Range: -1.1846

Max Act: 1.1846. Min Act: -0.0000

Data Index: 856286 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0716. Min Act: -0.0000

Data Index: 663953 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.9747. Min Act: -0.0000

Data Index: 416339 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.8463. Min Act: -0.0001

Data Index: 934641 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.8430. Min Act: -0.0001

Data Index: 1269979 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.8686. Min Act: -0.0000

Data Index: 840675 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.8116. Min Act: -0.0001

Data Index: 776940 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.7831. Min Act: -0.0001

Data Index: 619488 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.7360. Min Act: -0.0000

Data Index: 1279181 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.7789. Min Act: -0.0000

Data Index: 951139 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.7750. Min Act: -0.0000

Data Index: 936276 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.8249. Min Act: -0.0000

Data Index: 219975 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.8248. Min Act: -0.0001

Data Index: 921394 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.7907. Min Act: -0.0000

Data Index: 1194890 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.7911. Min Act: -0.0001

Data Index: 1139685 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.7642. Min Act: -0.0000

Data Index: 903739 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.7534. Min Act: -0.0000

Data Index: 196694 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.8030. Min Act: -0.0000

Data Index: 1245024 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.7453. Min Act: -0.0000

Data Index: 797828 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.7936. Min Act: -0.0001

Data Index: 349949 (C4 (Web Text))

Max Activating Token Index: 516