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

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

Neuron 717 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1584. Min Range: -3.1584

Max Act: 3.1584. Min Act: -0.0001

Data Index: 1391341 (Python Code)

Max Activating Token Index: 796

Text #1

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.9004. Min Act: -0.0001

Data Index: 1549609 (Python Code)

Max Activating Token Index: 806

Text #2

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.6968. Min Act: -0.0001

Data Index: 1592296 (Python Code)

Max Activating Token Index: 788

Text #3

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.6643. Min Act: -0.0001

Data Index: 1603380 (Python Code)

Max Activating Token Index: 445

Text #4

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.7601. Min Act: -0.0001

Data Index: 1376667 (Python Code)

Max Activating Token Index: 705

Text #5

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.6936. Min Act: -0.0001

Data Index: 247590 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.6213. Min Act: -0.0001

Data Index: 1455247 (Python Code)

Max Activating Token Index: 213

Text #7

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.7029. Min Act: -0.0001

Data Index: 1483486 (Python Code)

Max Activating Token Index: 152

Text #8

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.6238. Min Act: -0.0001

Data Index: 227785 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.6373. Min Act: -0.0001

Data Index: 1380295 (Python Code)

Max Activating Token Index: 221

Text #10

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.8079. Min Act: -0.0001

Data Index: 1522502 (Python Code)

Max Activating Token Index: 936

Text #11

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.6871. Min Act: -0.0001

Data Index: 1427020 (Python Code)

Max Activating Token Index: 815

Text #12

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.6324. Min Act: -0.0001

Data Index: 1646028 (Python Code)

Max Activating Token Index: 922

Text #13

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.5601. Min Act: -0.0001

Data Index: 1405557 (Python Code)

Max Activating Token Index: 988

Text #14

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.6646. Min Act: -0.0000

Data Index: 1141439 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.5683. Min Act: -0.0001

Data Index: 1369026 (Python Code)

Max Activating Token Index: 942

Text #16

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.3941. Min Act: -0.0001

Data Index: 1431063 (Python Code)

Max Activating Token Index: 771

Text #17

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.7153. Min Act: -0.0001

Data Index: 1406244 (Python Code)

Max Activating Token Index: 545

Text #18

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.5173. Min Act: -0.0000

Data Index: 683277 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 3.1584. Min Range: -3.1584

Max Act: 2.5730. Min Act: -0.0001

Data Index: 1611485 (Python Code)

Max Activating Token Index: 787