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

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

Neuron 2415 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.3897. Min Act: -0.0000

Data Index: 1554772 (Python Code)

Max Activating Token Index: 757

Text #1

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.1238. Min Act: -0.0000

Data Index: 1626561 (Python Code)

Max Activating Token Index: 525

Text #2

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.0419. Min Act: -0.0000

Data Index: 1419588 (Python Code)

Max Activating Token Index: 1013

Text #3

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.9686. Min Act: -0.0000

Data Index: 1582868 (Python Code)

Max Activating Token Index: 701

Text #4

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.9008. Min Act: -0.0000

Data Index: 1604339 (Python Code)

Max Activating Token Index: 788

Text #5

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.7651. Min Act: -0.0000

Data Index: 1552277 (Python Code)

Max Activating Token Index: 831

Text #6

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.7615. Min Act: -0.0000

Data Index: 1475046 (Python Code)

Max Activating Token Index: 316

Text #7

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.6912. Min Act: -0.0000

Data Index: 1606625 (Python Code)

Max Activating Token Index: 632

Text #8

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.7408. Min Act: -0.0000

Data Index: 1476915 (Python Code)

Max Activating Token Index: 951

Text #9

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.3541. Min Act: -0.0000

Data Index: 1508042 (Python Code)

Max Activating Token Index: 767

Text #10

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.4029. Min Act: -0.0000

Data Index: 1604824 (Python Code)

Max Activating Token Index: 228

Text #11

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.3531. Min Act: -0.0000

Data Index: 1571874 (Python Code)

Max Activating Token Index: 373

Text #12

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.5140. Min Act: -0.0000

Data Index: 1367331 (Python Code)

Max Activating Token Index: 508

Text #13

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.3931. Min Act: -0.0000

Data Index: 1372791 (Python Code)

Max Activating Token Index: 246

Text #14

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.3288. Min Act: -0.0000

Data Index: 1466027 (Python Code)

Max Activating Token Index: 308

Text #15

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.3580. Min Act: -0.0000

Data Index: 1429252 (Python Code)

Max Activating Token Index: 778

Text #16

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.2788. Min Act: -0.0000

Data Index: 1399644 (Python Code)

Max Activating Token Index: 756

Text #17

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.3579. Min Act: -0.0000

Data Index: 1623712 (Python Code)

Max Activating Token Index: 585

Text #18

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.3471. Min Act: -0.0000

Data Index: 1558923 (Python Code)

Max Activating Token Index: 639

Text #19

Max Range: 2.3897. Min Range: -2.3897

Max Act: 1.2122. Min Act: -0.0000

Data Index: 1419317 (Python Code)

Max Activating Token Index: 992