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

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

Neuron 2255 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5450. Min Range: -2.5450

Max Act: 2.5450. Min Act: -0.0000

Data Index: 813670 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.9724. Min Act: -0.0000

Data Index: 1209244 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.8902. Min Act: -0.0000

Data Index: 1250385 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.6663. Min Act: -0.0000

Data Index: 1320082 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.7852. Min Act: -0.0000

Data Index: 276286 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.4763. Min Act: -0.0000

Data Index: 529193 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.5811. Min Act: -0.0000

Data Index: 637234 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.2998. Min Act: -0.0000

Data Index: 1649364 (Python Code)

Max Activating Token Index: 808

Text #8

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.3561. Min Act: -0.0000

Data Index: 1116578 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.6021. Min Act: -0.0000

Data Index: 422654 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.2131. Min Act: -0.0000

Data Index: 706319 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.2786. Min Act: -0.0000

Data Index: 85734 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.1900. Min Act: -0.0000

Data Index: 1151626 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.2051. Min Act: -0.0000

Data Index: 56683 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.0620. Min Act: -0.0000

Data Index: 64405 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.0829. Min Act: -0.0000

Data Index: 458247 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1301823 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.0059. Min Act: -0.0000

Data Index: 113198 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 2.5450. Min Range: -2.5450

Max Act: 1.0120. Min Act: -0.0000

Data Index: 1588083 (Python Code)

Max Activating Token Index: 236

Text #19

Max Range: 2.5450. Min Range: -2.5450

Max Act: 0.9477. Min Act: -0.0000

Data Index: 697813 (C4 (Web Text))

Max Activating Token Index: 572