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

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

Neuron 2841 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2458. Min Act: -0.0001

Data Index: 125188 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2319. Min Act: -0.0001

Data Index: 957580 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2349. Min Act: -0.0001

Data Index: 985410 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2273. Min Act: -0.0001

Data Index: 1141706 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1966. Min Act: -0.0001

Data Index: 1235540 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1839. Min Act: -0.0001

Data Index: 175765 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1841. Min Act: -0.0001

Data Index: 49161 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1804. Min Act: -0.0001

Data Index: 900559 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1635. Min Act: -0.0001

Data Index: 289686 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1599. Min Act: -0.0001

Data Index: 628465 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1611. Min Act: -0.0001

Data Index: 915124 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1621. Min Act: -0.0001

Data Index: 771823 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1595. Min Act: -0.0001

Data Index: 783849 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1579. Min Act: -0.0001

Data Index: 433996 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1593. Min Act: -0.0001

Data Index: 348242 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1586. Min Act: -0.0001

Data Index: 427784 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1524. Min Act: -0.0001

Data Index: 723448 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1471. Min Act: -0.0001

Data Index: 280537 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1614. Min Act: -0.0001

Data Index: 642037 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1566. Min Act: -0.0001

Data Index: 1294875 (C4 (Web Text))

Max Activating Token Index: 914