Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 613 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.4359. Min Act: -0.0000

Data Index: 140509 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.5387. Min Act: -0.0000

Data Index: 1138368 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.8413. Min Act: -0.0000

Data Index: 813001 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.4420. Min Act: -0.0000

Data Index: 103007 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.1456. Min Act: -0.0000

Data Index: 262581 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6512. Min Act: -0.0000

Data Index: 105407 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.3520. Min Act: -0.0000

Data Index: 1184317 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.3557. Min Act: -0.0000

Data Index: 1182444 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.3993. Min Act: -0.0000

Data Index: 632717 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.1043. Min Act: -0.0000

Data Index: 177531 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.2362. Min Act: -0.0000

Data Index: 89034 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.1852. Min Act: -0.0000

Data Index: 24607 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 3.8413. Min Range: -3.8413

Max Act: 2.8678. Min Act: -0.0000

Data Index: 115017 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.1666. Min Act: -0.0000

Data Index: 509109 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.0045. Min Act: -0.0000

Data Index: 269564 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.1154. Min Act: -0.0000

Data Index: 1184882 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.2224. Min Act: -0.0000

Data Index: 429744 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 3.8413. Min Range: -3.8413

Max Act: 2.9458. Min Act: -0.0000

Data Index: 167722 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.3959. Min Act: -0.0000

Data Index: 201737 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 3.8413. Min Range: -3.8413

Max Act: 2.6702. Min Act: -0.0000

Data Index: 834845 (C4 (Web Text))

Max Activating Token Index: 606