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

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

Neuron 1575 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.8340. Min Act: -0.0000

Data Index: 633324 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7606. Min Act: -0.0000

Data Index: 897032 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7598. Min Act: -0.0000

Data Index: 281181 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.6955. Min Act: -0.0000

Data Index: 366153 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.6836. Min Act: -0.0000

Data Index: 74774 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1266264 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1128961 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.6353. Min Act: -0.0000

Data Index: 213074 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.6352. Min Act: -0.0000

Data Index: 697497 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.5659. Min Act: -0.0000

Data Index: 1310652 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1251882 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1429882 (Python Code)

Max Activating Token Index: 948

Text #12

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1586641 (Python Code)

Max Activating Token Index: 669

Text #13

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.4661. Min Act: -0.0000

Data Index: 203962 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1430425 (Python Code)

Max Activating Token Index: 810

Text #15

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.4299. Min Act: -0.0000

Data Index: 1426419 (Python Code)

Max Activating Token Index: 144

Text #16

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1508230 (Python Code)

Max Activating Token Index: 761

Text #17

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1568975 (Python Code)

Max Activating Token Index: 126

Text #18

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1381613 (Python Code)

Max Activating Token Index: 631

Text #19

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1386801 (Python Code)

Max Activating Token Index: 775