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

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

Neuron 2710 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1306999 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1636435 (Python Code)

Max Activating Token Index: 540

Text #2

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1771. Min Act: -0.0000

Data Index: 888683 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1500008 (Python Code)

Max Activating Token Index: 94

Text #4

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1619291 (Python Code)

Max Activating Token Index: 491

Text #5

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1690. Min Act: -0.0000

Data Index: 960276 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1631. Min Act: -0.0000

Data Index: 1343810 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1458. Min Act: -0.0000

Data Index: 1539810 (Python Code)

Max Activating Token Index: 895

Text #8

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1475471 (Python Code)

Max Activating Token Index: 621

Text #9

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1419. Min Act: -0.0000

Data Index: 677896 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1574145 (Python Code)

Max Activating Token Index: 713

Text #11

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1425. Min Act: -0.0000

Data Index: 970232 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1613116 (Python Code)

Max Activating Token Index: 858

Text #13

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1367. Min Act: -0.0000

Data Index: 469607 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1140471 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1285. Min Act: -0.0000

Data Index: 1241233 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1515. Min Act: -0.0000

Data Index: 966898 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1354. Min Act: -0.0000

Data Index: 686678 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1345. Min Act: -0.0000

Data Index: 632251 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1277. Min Act: -0.0000

Data Index: 203147 (C4 (Web Text))

Max Activating Token Index: 826