Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3540 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.8127. Min Act: -0.0000

Data Index: 1512613 (Python Code)

Max Activating Token Index: 907

Text #1

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.6360. Min Act: -0.0000

Data Index: 1504254 (Python Code)

Max Activating Token Index: 433

Text #2

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.4004. Min Act: -0.0000

Data Index: 1453087 (Python Code)

Max Activating Token Index: 486

Text #3

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.3551. Min Act: -0.0000

Data Index: 1521772 (Python Code)

Max Activating Token Index: 563

Text #4

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.4237. Min Act: -0.0000

Data Index: 1489092 (Python Code)

Max Activating Token Index: 925

Text #5

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.3524. Min Act: -0.0000

Data Index: 1594465 (Python Code)

Max Activating Token Index: 760

Text #6

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.3175. Min Act: -0.0000

Data Index: 1391686 (Python Code)

Max Activating Token Index: 685

Text #7

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1481938 (Python Code)

Max Activating Token Index: 813

Text #8

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.3696. Min Act: -0.0000

Data Index: 1415380 (Python Code)

Max Activating Token Index: 822

Text #9

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.2643. Min Act: -0.0000

Data Index: 1632643 (Python Code)

Max Activating Token Index: 718

Text #10

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.2461. Min Act: -0.0000

Data Index: 1653682 (Python Code)

Max Activating Token Index: 473

Text #11

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.1753. Min Act: -0.0000

Data Index: 1369780 (Python Code)

Max Activating Token Index: 235

Text #12

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.1519. Min Act: -0.0000

Data Index: 1476764 (Python Code)

Max Activating Token Index: 641

Text #13

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.2726. Min Act: -0.0000

Data Index: 1541635 (Python Code)

Max Activating Token Index: 801

Text #14

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.1112. Min Act: -0.0000

Data Index: 1368704 (Python Code)

Max Activating Token Index: 341

Text #15

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.1114. Min Act: -0.0000

Data Index: 1653768 (Python Code)

Max Activating Token Index: 184

Text #16

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.2605. Min Act: -0.0000

Data Index: 1407837 (Python Code)

Max Activating Token Index: 166

Text #17

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1547254 (Python Code)

Max Activating Token Index: 276

Text #18

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.1456. Min Act: -0.0000

Data Index: 1384847 (Python Code)

Max Activating Token Index: 292

Text #19

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.1535. Min Act: -0.0000

Data Index: 1514980 (Python Code)

Max Activating Token Index: 190