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

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

Neuron 348 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.4035. Min Act: -0.0001

Data Index: 1587164 (Python Code)

Max Activating Token Index: 17

Text #1

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.3836. Min Act: -0.0001

Data Index: 1375089 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.3624. Min Act: -0.0002

Data Index: 300315 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.3407. Min Act: -0.0001

Data Index: 1521963 (Python Code)

Max Activating Token Index: 2

Text #4

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.3501. Min Act: -0.0001

Data Index: 1385756 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.3431. Min Act: -0.0001

Data Index: 1490863 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.3149. Min Act: -0.0001

Data Index: 308540 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.3234. Min Act: -0.0002

Data Index: 986654 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2978. Min Act: -0.0001

Data Index: 1581434 (Python Code)

Max Activating Token Index: 76

Text #9

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.3120. Min Act: -0.0001

Data Index: 1417507 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2903. Min Act: -0.0001

Data Index: 610245 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2813. Min Act: -0.0001

Data Index: 741397 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2824. Min Act: -0.0001

Data Index: 1592532 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2683. Min Act: -0.0001

Data Index: 1564944 (Python Code)

Max Activating Token Index: 2

Text #14

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2665. Min Act: -0.0002

Data Index: 30570 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2731. Min Act: -0.0002

Data Index: 690519 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2712. Min Act: -0.0001

Data Index: 1475364 (Python Code)

Max Activating Token Index: 114

Text #17

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2726. Min Act: -0.0001

Data Index: 465602 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2775. Min Act: -0.0002

Data Index: 764745 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.4035. Min Range: -0.4035

Max Act: 0.2687. Min Act: -0.0001

Data Index: 799928 (C4 (Web Text))

Max Activating Token Index: 695