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

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

Neuron 2915 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0549. Min Range: -1.0549

Max Act: 1.0549. Min Act: -0.0001

Data Index: 892252 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 1.0549. Min Range: -1.0549

Max Act: 1.0311. Min Act: -0.0001

Data Index: 1138248 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.9979. Min Act: -0.0001

Data Index: 341298 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.9927. Min Act: -0.0001

Data Index: 650841 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.9885. Min Act: -0.0001

Data Index: 690335 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.9871. Min Act: -0.0001

Data Index: 924751 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.9816. Min Act: -0.0001

Data Index: 776499 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.9013. Min Act: -0.0001

Data Index: 573315 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8747. Min Act: -0.0001

Data Index: 858370 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8433. Min Act: -0.0001

Data Index: 165748 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8845. Min Act: -0.0001

Data Index: 149515 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.9546. Min Act: -0.0001

Data Index: 1217434 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.9020. Min Act: -0.0001

Data Index: 189646 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8577. Min Act: -0.0001

Data Index: 329988 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8577. Min Act: -0.0001

Data Index: 1044222 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8511. Min Act: -0.0001

Data Index: 363909 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8250. Min Act: -0.0001

Data Index: 33833 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8452. Min Act: -0.0001

Data Index: 1144101 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8188. Min Act: -0.0001

Data Index: 579347 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 1.0549. Min Range: -1.0549

Max Act: 0.8392. Min Act: -0.0001

Data Index: 1204959 (C4 (Web Text))

Max Activating Token Index: 894