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

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

Neuron 5139 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2412. Min Range: -1.2412

Max Act: 1.2206. Min Act: -0.0000

Data Index: 884972 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 1.2412. Min Range: -1.2412

Max Act: 1.2412. Min Act: -0.0000

Data Index: 722671 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.9775. Min Act: -0.0000

Data Index: 905817 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1079538 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.9140. Min Act: -0.0000

Data Index: 608858 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.9817. Min Act: -0.0000

Data Index: 754965 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.8728. Min Act: -0.0000

Data Index: 1216578 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1219664 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.7651. Min Act: -0.0000

Data Index: 193818 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.7107. Min Act: -0.0000

Data Index: 610822 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1049727 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.6947. Min Act: -0.0000

Data Index: 893732 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.6706. Min Act: 0.0000

Data Index: 1332930 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.6316. Min Act: -0.0000

Data Index: 619734 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.6180. Min Act: 0.0000

Data Index: 602481 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1361372 (Python Code)

Max Activating Token Index: 737

Text #16

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.5927. Min Act: -0.0000

Data Index: 113554 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.6427. Min Act: -0.0000

Data Index: 811759 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1307837 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.5895. Min Act: -0.0000

Data Index: 191849 (C4 (Web Text))

Max Activating Token Index: 750