Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3685 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.8699. Min Act: -0.0001

Data Index: 1410919 (Python Code)

Max Activating Token Index: 889

Text #1

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.8007. Min Act: -0.0001

Data Index: 1397211 (Python Code)

Max Activating Token Index: 585

Text #2

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.7585. Min Act: -0.0001

Data Index: 1576551 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.7815. Min Act: -0.0001

Data Index: 1592708 (Python Code)

Max Activating Token Index: 701

Text #4

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.7677. Min Act: -0.0001

Data Index: 1402531 (Python Code)

Max Activating Token Index: 105

Text #5

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.7754. Min Act: -0.0001

Data Index: 1421506 (Python Code)

Max Activating Token Index: 718

Text #6

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6700. Min Act: -0.0001

Data Index: 1616516 (Python Code)

Max Activating Token Index: 760

Text #7

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6924. Min Act: -0.0001

Data Index: 1449178 (Python Code)

Max Activating Token Index: 184

Text #8

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.7120. Min Act: -0.0001

Data Index: 1422459 (Python Code)

Max Activating Token Index: 13

Text #9

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6555. Min Act: -0.0001

Data Index: 1508217 (Python Code)

Max Activating Token Index: 121

Text #10

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6725. Min Act: -0.0001

Data Index: 1640686 (Python Code)

Max Activating Token Index: 585

Text #11

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6699. Min Act: -0.0001

Data Index: 1441974 (Python Code)

Max Activating Token Index: 38

Text #12

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6655. Min Act: -0.0001

Data Index: 1359854 (Python Code)

Max Activating Token Index: 340

Text #13

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6547. Min Act: -0.0001

Data Index: 1610445 (Python Code)

Max Activating Token Index: 331

Text #14

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6708. Min Act: -0.0001

Data Index: 1393547 (Python Code)

Max Activating Token Index: 60

Text #15

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6258. Min Act: -0.0001

Data Index: 1415072 (Python Code)

Max Activating Token Index: 580

Text #16

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6467. Min Act: -0.0001

Data Index: 1501722 (Python Code)

Max Activating Token Index: 39

Text #17

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6413. Min Act: -0.0001

Data Index: 1583766 (Python Code)

Max Activating Token Index: 267

Text #18

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6259. Min Act: -0.0001

Data Index: 1509429 (Python Code)

Max Activating Token Index: 216

Text #19

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6161. Min Act: -0.0001

Data Index: 1620545 (Python Code)

Max Activating Token Index: 287