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

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

Neuron 1221 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.6429. Min Act: -0.0000

Data Index: 1585357 (Python Code)

Max Activating Token Index: 846

Text #1

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.3657. Min Act: -0.0000

Data Index: 1605583 (Python Code)

Max Activating Token Index: 876

Text #2

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.2219. Min Act: -0.0000

Data Index: 1500224 (Python Code)

Max Activating Token Index: 86

Text #3

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.1589. Min Act: -0.0000

Data Index: 1573913 (Python Code)

Max Activating Token Index: 713

Text #4

Max Range: 4.6429. Min Range: -4.6429

Max Act: 3.8757. Min Act: -0.0000

Data Index: 1513685 (Python Code)

Max Activating Token Index: 987

Text #5

Max Range: 4.6429. Min Range: -4.6429

Max Act: 3.4574. Min Act: -0.0000

Data Index: 1398600 (Python Code)

Max Activating Token Index: 591

Text #6

Max Range: 4.6429. Min Range: -4.6429

Max Act: 3.1673. Min Act: -0.0000

Data Index: 1598757 (Python Code)

Max Activating Token Index: 562

Text #7

Max Range: 4.6429. Min Range: -4.6429

Max Act: 3.0075. Min Act: -0.0000

Data Index: 1561725 (Python Code)

Max Activating Token Index: 675

Text #8

Max Range: 4.6429. Min Range: -4.6429

Max Act: 2.9908. Min Act: -0.0000

Data Index: 1442432 (Python Code)

Max Activating Token Index: 915

Text #9

Max Range: 4.6429. Min Range: -4.6429

Max Act: 3.1320. Min Act: -0.0000

Data Index: 1436127 (Python Code)

Max Activating Token Index: 939

Text #10

Max Range: 4.6429. Min Range: -4.6429

Max Act: 3.2632. Min Act: -0.0000

Data Index: 1618030 (Python Code)

Max Activating Token Index: 435

Text #11

Max Range: 4.6429. Min Range: -4.6429

Max Act: 2.8313. Min Act: -0.0000

Data Index: 1512384 (Python Code)

Max Activating Token Index: 647

Text #12

Max Range: 4.6429. Min Range: -4.6429

Max Act: 2.7053. Min Act: -0.0000

Data Index: 1526441 (Python Code)

Max Activating Token Index: 491

Text #13

Max Range: 4.6429. Min Range: -4.6429

Max Act: 2.6393. Min Act: -0.0000

Data Index: 1372759 (Python Code)

Max Activating Token Index: 459

Text #14

Max Range: 4.6429. Min Range: -4.6429

Max Act: 2.5538. Min Act: -0.0000

Data Index: 1468522 (Python Code)

Max Activating Token Index: 166

Text #15

Max Range: 4.6429. Min Range: -4.6429

Max Act: 2.2868. Min Act: -0.0000

Data Index: 1432326 (Python Code)

Max Activating Token Index: 765

Text #16

Max Range: 4.6429. Min Range: -4.6429

Max Act: 2.3546. Min Act: -0.0000

Data Index: 1590895 (Python Code)

Max Activating Token Index: 204

Text #17

Max Range: 4.6429. Min Range: -4.6429

Max Act: 2.3325. Min Act: -0.0000

Data Index: 1642344 (Python Code)

Max Activating Token Index: 102

Text #18

Max Range: 4.6429. Min Range: -4.6429

Max Act: 2.2403. Min Act: -0.0000

Data Index: 1386612 (Python Code)

Max Activating Token Index: 445

Text #19

Max Range: 4.6429. Min Range: -4.6429

Max Act: 2.1884. Min Act: -0.0000

Data Index: 1393089 (Python Code)

Max Activating Token Index: 192