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

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

Neuron 3359 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1953. Min Act: -0.0000

Data Index: 414448 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1030939 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1681. Min Act: -0.0001

Data Index: 840254 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1705. Min Act: -0.0001

Data Index: 331382 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1573. Min Act: -0.0000

Data Index: 114500 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1077924 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1620. Min Act: -0.0001

Data Index: 927937 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1660. Min Act: -0.0000

Data Index: 125042 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1585. Min Act: -0.0000

Data Index: 908220 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1670. Min Act: -0.0001

Data Index: 954845 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1548. Min Act: -0.0001

Data Index: 627749 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1084717 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1530. Min Act: -0.0001

Data Index: 826453 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1541. Min Act: -0.0000

Data Index: 840437 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1439. Min Act: -0.0001

Data Index: 1020435 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1552. Min Act: -0.0000

Data Index: 754101 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1529. Min Act: -0.0001

Data Index: 204561 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1462. Min Act: -0.0001

Data Index: 896542 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1459. Min Act: -0.0001

Data Index: 581971 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1492. Min Act: -0.0001

Data Index: 678146 (C4 (Web Text))

Max Activating Token Index: 724