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

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

Neuron 2630 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1535446 (Python Code)

Max Activating Token Index: 504

Text #1

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1613649 (Python Code)

Max Activating Token Index: 828

Text #2

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1584096 (Python Code)

Max Activating Token Index: 964

Text #3

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1477634 (Python Code)

Max Activating Token Index: 659

Text #4

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1656275 (Python Code)

Max Activating Token Index: 81

Text #5

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1119032 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1580202 (Python Code)

Max Activating Token Index: 669

Text #7

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6586. Min Act: -0.0000

Data Index: 859129 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5623. Min Act: -0.0000

Data Index: 833292 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1382300 (Python Code)

Max Activating Token Index: 777

Text #10

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1446118 (Python Code)

Max Activating Token Index: 322

Text #11

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1538538 (Python Code)

Max Activating Token Index: 753

Text #12

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5712. Min Act: -0.0000

Data Index: 615132 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5983. Min Act: -0.0000

Data Index: 382670 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1535925 (Python Code)

Max Activating Token Index: 320

Text #15

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6054. Min Act: -0.0000

Data Index: 1044286 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1522111 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1587729 (Python Code)

Max Activating Token Index: 823

Text #18

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5682. Min Act: -0.0000

Data Index: 610629 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5792. Min Act: -0.0000

Data Index: 750853 (C4 (Web Text))

Max Activating Token Index: 255