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

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

Neuron 890 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.8976. Min Act: -0.0001

Data Index: 370914 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.8972. Min Act: -0.0001

Data Index: 486572 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7654. Min Act: -0.0001

Data Index: 379070 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.8414. Min Act: -0.0001

Data Index: 1357451 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7822. Min Act: -0.0001

Data Index: 612339 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1065617 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7302. Min Act: -0.0001

Data Index: 259467 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.8297. Min Act: -0.0001

Data Index: 1134488 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.8067. Min Act: -0.0001

Data Index: 558143 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7301. Min Act: -0.0001

Data Index: 1231384 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7477. Min Act: -0.0001

Data Index: 1102732 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6799. Min Act: -0.0001

Data Index: 377631 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7462. Min Act: -0.0001

Data Index: 672852 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7385. Min Act: -0.0001

Data Index: 1273178 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7108. Min Act: -0.0001

Data Index: 944765 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6373. Min Act: -0.0001

Data Index: 1350813 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6786. Min Act: -0.0000

Data Index: 497691 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7505. Min Act: -0.0001

Data Index: 956409 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7177. Min Act: -0.0001

Data Index: 1270774 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7402. Min Act: -0.0001

Data Index: 1333239 (C4 (Web Text))

Max Activating Token Index: 466