Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3898 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0835. Min Act: -0.0000

Data Index: 1529119 (Python Code)

Max Activating Token Index: 645

Text #1

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0781. Min Act: -0.0001

Data Index: 779711 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0629. Min Act: -0.0000

Data Index: 663086 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1295119 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0601. Min Act: -0.0000

Data Index: 1063645 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0557. Min Act: -0.0000

Data Index: 691296 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0489. Min Act: -0.0000

Data Index: 1403795 (Python Code)

Max Activating Token Index: 694

Text #7

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1096954 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0449. Min Act: -0.0000

Data Index: 1617548 (Python Code)

Max Activating Token Index: 818

Text #9

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0498. Min Act: -0.0000

Data Index: 174186 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0480. Min Act: -0.0001

Data Index: 174739 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0461. Min Act: -0.0000

Data Index: 1608186 (Python Code)

Max Activating Token Index: 803

Text #12

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0455. Min Act: -0.0000

Data Index: 1523967 (Python Code)

Max Activating Token Index: 217

Text #13

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1606027 (Python Code)

Max Activating Token Index: 734

Text #14

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1637856 (Python Code)

Max Activating Token Index: 989

Text #15

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0444. Min Act: -0.0000

Data Index: 907896 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0411. Min Act: -0.0000

Data Index: 448199 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0421. Min Act: -0.0000

Data Index: 1087592 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0451. Min Act: -0.0000

Data Index: 1106789 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0426. Min Act: -0.0000

Data Index: 1426526 (Python Code)

Max Activating Token Index: 821