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

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

Neuron 4453 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3542. Min Range: -2.3542

Max Act: 2.3542. Min Act: -0.0000

Data Index: 1435881 (Python Code)

Max Activating Token Index: 899

Text #1

Max Range: 2.3542. Min Range: -2.3542

Max Act: 2.0997. Min Act: -0.0000

Data Index: 1541929 (Python Code)

Max Activating Token Index: 17

Text #2

Max Range: 2.3542. Min Range: -2.3542

Max Act: 2.0703. Min Act: -0.0000

Data Index: 1454713 (Python Code)

Max Activating Token Index: 681

Text #3

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.7744. Min Act: -0.0000

Data Index: 1490754 (Python Code)

Max Activating Token Index: 87

Text #4

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.8932. Min Act: -0.0000

Data Index: 1443256 (Python Code)

Max Activating Token Index: 438

Text #5

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.7132. Min Act: -0.0000

Data Index: 1379804 (Python Code)

Max Activating Token Index: 300

Text #6

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.7391. Min Act: -0.0000

Data Index: 1424160 (Python Code)

Max Activating Token Index: 913

Text #7

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.7196. Min Act: -0.0000

Data Index: 1518656 (Python Code)

Max Activating Token Index: 646

Text #8

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.9031. Min Act: -0.0000

Data Index: 1455495 (Python Code)

Max Activating Token Index: 274

Text #9

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.7100. Min Act: -0.0000

Data Index: 1653106 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.7176. Min Act: -0.0001

Data Index: 1568600 (Python Code)

Max Activating Token Index: 279

Text #11

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.6917. Min Act: 0.0000

Data Index: 1417969 (Python Code)

Max Activating Token Index: 107

Text #12

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.5994. Min Act: -0.0000

Data Index: 1418170 (Python Code)

Max Activating Token Index: 85

Text #13

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.5947. Min Act: -0.0000

Data Index: 1569406 (Python Code)

Max Activating Token Index: 43

Text #14

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.6781. Min Act: -0.0000

Data Index: 1501376 (Python Code)

Max Activating Token Index: 389

Text #15

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.5691. Min Act: -0.0000

Data Index: 1481245 (Python Code)

Max Activating Token Index: 642

Text #16

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.6069. Min Act: -0.0000

Data Index: 1637653 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.5257. Min Act: -0.0000

Data Index: 1468733 (Python Code)

Max Activating Token Index: 243

Text #18

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.5446. Min Act: -0.0000

Data Index: 1626705 (Python Code)

Max Activating Token Index: 231

Text #19

Max Range: 2.3542. Min Range: -2.3542

Max Act: 1.5802. Min Act: -0.0000

Data Index: 1388420 (Python Code)

Max Activating Token Index: 524