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

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

Neuron 1931 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.2255. Min Act: -0.0001

Data Index: 1534239 (Python Code)

Max Activating Token Index: 867

Text #1

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.2078. Min Act: -0.0000

Data Index: 826000 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1915. Min Act: -0.0001

Data Index: 1482163 (Python Code)

Max Activating Token Index: 457

Text #3

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1915. Min Act: -0.0000

Data Index: 423014 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1769. Min Act: -0.0001

Data Index: 838040 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1764. Min Act: -0.0001

Data Index: 1108416 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1535041 (Python Code)

Max Activating Token Index: 445

Text #7

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1838. Min Act: -0.0001

Data Index: 309682 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1672. Min Act: -0.0001

Data Index: 448216 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1649. Min Act: -0.0000

Data Index: 182781 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1147706 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1620. Min Act: -0.0001

Data Index: 957181 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1550. Min Act: -0.0001

Data Index: 422149 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1479. Min Act: -0.0000

Data Index: 1022635 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1610. Min Act: -0.0001

Data Index: 10814 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1516. Min Act: -0.0000

Data Index: 142795 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1620. Min Act: -0.0001

Data Index: 1232993 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1655. Min Act: -0.0000

Data Index: 1593354 (Python Code)

Max Activating Token Index: 867

Text #18

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1561. Min Act: -0.0001

Data Index: 767208 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1611. Min Act: -0.0001

Data Index: 794534 (C4 (Web Text))

Max Activating Token Index: 606