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

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

Neuron 4956 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.9015. Min Act: -0.0001

Data Index: 63296 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.7924. Min Act: -0.0001

Data Index: 1228667 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.7755. Min Act: -0.0001

Data Index: 523610 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.7286. Min Act: -0.0001

Data Index: 251458 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.7430. Min Act: -0.0001

Data Index: 1554835 (Python Code)

Max Activating Token Index: 136

Text #5

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6799. Min Act: -0.0001

Data Index: 110464 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6976. Min Act: -0.0001

Data Index: 248416 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6673. Min Act: -0.0001

Data Index: 1280928 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6474. Min Act: -0.0001

Data Index: 401399 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6630. Min Act: -0.0001

Data Index: 483047 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6413. Min Act: -0.0001

Data Index: 1182180 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.7190. Min Act: -0.0001

Data Index: 896811 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6885. Min Act: -0.0001

Data Index: 346039 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6652. Min Act: -0.0001

Data Index: 532117 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6185. Min Act: -0.0001

Data Index: 32873 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6708. Min Act: -0.0001

Data Index: 406571 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6672. Min Act: -0.0001

Data Index: 706350 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6648. Min Act: -0.0001

Data Index: 694548 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6581. Min Act: -0.0001

Data Index: 1257607 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6480. Min Act: -0.0001

Data Index: 1533499 (Python Code)

Max Activating Token Index: 763