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

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

Neuron 2784 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5942. Min Range: -1.5942

Max Act: 1.5189. Min Act: -0.0000

Data Index: 746904 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.5942. Min Range: -1.5942

Max Act: 1.4929. Min Act: -0.0000

Data Index: 1405143 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 1.5942. Min Range: -1.5942

Max Act: 1.5942. Min Act: -0.0000

Data Index: 226051 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 1.5942. Min Range: -1.5942

Max Act: 1.3899. Min Act: -0.0000

Data Index: 1322503 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 1.5942. Min Range: -1.5942

Max Act: 1.0845. Min Act: -0.0000

Data Index: 477977 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.5942. Min Range: -1.5942

Max Act: 1.1461. Min Act: -0.0000

Data Index: 1101813 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 1.5942. Min Range: -1.5942

Max Act: 1.0848. Min Act: -0.0000

Data Index: 781458 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 1.5942. Min Range: -1.5942

Max Act: 1.0716. Min Act: -0.0000

Data Index: 500346 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 1.5942. Min Range: -1.5942

Max Act: 1.0347. Min Act: -0.0000

Data Index: 1236538 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 1.5942. Min Range: -1.5942

Max Act: 1.1373. Min Act: -0.0000

Data Index: 1583419 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 1.5942. Min Range: -1.5942

Max Act: 1.1373. Min Act: -0.0000

Data Index: 1371785 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 1.5942. Min Range: -1.5942

Max Act: 1.0524. Min Act: -0.0000

Data Index: 729613 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 1.5942. Min Range: -1.5942

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1410616 (Python Code)

Max Activating Token Index: 235

Text #13

Max Range: 1.5942. Min Range: -1.5942

Max Act: 1.0909. Min Act: -0.0000

Data Index: 334775 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 1.5942. Min Range: -1.5942

Max Act: 1.1536. Min Act: -0.0000

Data Index: 83167 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 1.5942. Min Range: -1.5942

Max Act: 0.9508. Min Act: -0.0000

Data Index: 610089 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 1.5942. Min Range: -1.5942

Max Act: 0.8718. Min Act: -0.0000

Data Index: 238842 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 1.5942. Min Range: -1.5942

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1392789 (Python Code)

Max Activating Token Index: 721

Text #18

Max Range: 1.5942. Min Range: -1.5942

Max Act: 0.8478. Min Act: -0.0000

Data Index: 459612 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 1.5942. Min Range: -1.5942

Max Act: 0.8817. Min Act: -0.0000

Data Index: 148919 (C4 (Web Text))

Max Activating Token Index: 707