Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4432 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1137244 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0505. Min Act: -0.0002

Data Index: 615715 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0510. Min Act: -0.0002

Data Index: 753163 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0500. Min Act: -0.0002

Data Index: 373986 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1008025 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0496. Min Act: -0.0002

Data Index: 864964 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0496. Min Act: -0.0002

Data Index: 355678 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0495. Min Act: -0.0002

Data Index: 195451 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1307187 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0494. Min Act: -0.0002

Data Index: 332515 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1204574 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1184469 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0494. Min Act: -0.0002

Data Index: 644619 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0494. Min Act: -0.0002

Data Index: 556000 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0493. Min Act: -0.0002

Data Index: 501065 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0493. Min Act: -0.0002

Data Index: 45425 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0493. Min Act: -0.0002

Data Index: 56056 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0492. Min Act: -0.0002

Data Index: 321453 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0493. Min Act: -0.0002

Data Index: 264391 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0501. Min Act: -0.0002

Data Index: 366793 (C4 (Web Text))

Max Activating Token Index: 4