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

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

Neuron 677 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: 0.2103. Min Range: -0.2103

Max Act: 0.2103. Min Act: -0.0003

Data Index: 326146 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1966. Min Act: -0.0003

Data Index: 26443 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1708. Min Act: -0.0003

Data Index: 215883 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1738. Min Act: -0.0003

Data Index: 227393 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1788. Min Act: -0.0003

Data Index: 12801 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1601. Min Act: -0.0003

Data Index: 613786 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1593. Min Act: -0.0003

Data Index: 777595 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1649. Min Act: -0.0003

Data Index: 846189 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1626. Min Act: -0.0003

Data Index: 584183 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1542. Min Act: -0.0003

Data Index: 729931 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1591. Min Act: -0.0003

Data Index: 378391 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1547. Min Act: -0.0003

Data Index: 1031274 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1545. Min Act: -0.0003

Data Index: 594956 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1488. Min Act: -0.0003

Data Index: 1011514 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1361. Min Act: -0.0003

Data Index: 190572 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1523. Min Act: -0.0003

Data Index: 1322636 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1464. Min Act: -0.0003

Data Index: 1127369 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1457. Min Act: -0.0003

Data Index: 277869 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1399. Min Act: -0.0003

Data Index: 980010 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1383. Min Act: -0.0003

Data Index: 640944 (C4 (Web Text))

Max Activating Token Index: 653