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

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

Neuron 3979 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.8585. Min Act: -0.0000

Data Index: 432468 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.8546. Min Act: -0.0000

Data Index: 555040 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.8267. Min Act: -0.0000

Data Index: 125079 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6438. Min Act: -0.0000

Data Index: 417775 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1026691 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1343803 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6215. Min Act: -0.0000

Data Index: 747842 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6445. Min Act: -0.0000

Data Index: 390793 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6614. Min Act: -0.0000

Data Index: 953100 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1059009 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1133263 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6356. Min Act: -0.0000

Data Index: 257621 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1061154 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1039607 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.5599. Min Act: -0.0000

Data Index: 20374 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.5584. Min Act: -0.0000

Data Index: 789724 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.5390. Min Act: -0.0000

Data Index: 485486 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.5277. Min Act: -0.0000

Data Index: 950136 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.5528. Min Act: -0.0000

Data Index: 306310 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1379610 (Python Code)

Max Activating Token Index: 249