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

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

Neuron 121 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.3622. Min Act: -0.0000

Data Index: 107005 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1597066 (Python Code)

Max Activating Token Index: 274

Text #2

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1114553 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2682. Min Act: -0.0000

Data Index: 506437 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2772. Min Act: -0.0000

Data Index: 882156 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1627881 (Python Code)

Max Activating Token Index: 229

Text #6

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2793. Min Act: -0.0000

Data Index: 83017 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1562386 (Python Code)

Max Activating Token Index: 794

Text #8

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2659. Min Act: -0.0000

Data Index: 28491 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1515702 (Python Code)

Max Activating Token Index: 61

Text #10

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2786. Min Act: -0.0000

Data Index: 648636 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1636700 (Python Code)

Max Activating Token Index: 549

Text #12

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1291515 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1205120 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2585. Min Act: -0.0000

Data Index: 663687 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2399. Min Act: -0.0000

Data Index: 1465158 (Python Code)

Max Activating Token Index: 562

Text #16

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2468. Min Act: -0.0000

Data Index: 1470123 (Python Code)

Max Activating Token Index: 245

Text #17

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2348. Min Act: -0.0000

Data Index: 160979 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1416776 (Python Code)

Max Activating Token Index: 103

Text #19

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1157038 (C4 (Web Text))

Max Activating Token Index: 509