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

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

Neuron 3978 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.8553. Min Act: -0.0000

Data Index: 471926 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7730. Min Act: -0.0000

Data Index: 1031838 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6912. Min Act: -0.0000

Data Index: 143441 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1192869 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6743. Min Act: -0.0001

Data Index: 1256486 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1140311 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6449. Min Act: -0.0001

Data Index: 1234016 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6043. Min Act: -0.0001

Data Index: 1235037 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1077106 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6356. Min Act: -0.0001

Data Index: 1337167 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6415. Min Act: -0.0000

Data Index: 1060851 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6152. Min Act: -0.0001

Data Index: 921494 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6271. Min Act: -0.0000

Data Index: 369998 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.5816. Min Act: -0.0001

Data Index: 410748 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1176059 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.5816. Min Act: -0.0001

Data Index: 1280883 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.5682. Min Act: -0.0000

Data Index: 941422 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.5855. Min Act: -0.0000

Data Index: 277621 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.5695. Min Act: -0.0001

Data Index: 978129 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.5863. Min Act: -0.0000

Data Index: 515124 (C4 (Web Text))

Max Activating Token Index: 485