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

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

Neuron 3578 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.2512. Min Act: -0.0000

Data Index: 603186 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.1898. Min Act: -0.0000

Data Index: 902259 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.8582. Min Act: -0.0000

Data Index: 797398 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.5816. Min Act: -0.0000

Data Index: 384238 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.3916. Min Act: -0.0000

Data Index: 1092053 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.2970. Min Act: -0.0000

Data Index: 1030558 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.4251. Min Act: -0.0000

Data Index: 1477424 (Python Code)

Max Activating Token Index: 362

Text #7

Max Range: 3.2512. Min Range: -3.2512

Max Act: 1.9120. Min Act: -0.0000

Data Index: 893073 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.0926. Min Act: -0.0000

Data Index: 202621 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.1985. Min Act: -0.0000

Data Index: 1620355 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.0713. Min Act: -0.0000

Data Index: 787969 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.1909. Min Act: -0.0000

Data Index: 1097009 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.2904. Min Act: -0.0000

Data Index: 766518 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.3668. Min Act: -0.0000

Data Index: 312831 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.0369. Min Act: -0.0000

Data Index: 620851 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.0457. Min Act: -0.0001

Data Index: 42130 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.0416. Min Act: -0.0000

Data Index: 1473114 (Python Code)

Max Activating Token Index: 365

Text #17

Max Range: 3.2512. Min Range: -3.2512

Max Act: 1.8232. Min Act: -0.0000

Data Index: 29115 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.2381. Min Act: -0.0000

Data Index: 1286475 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.1404. Min Act: -0.0000

Data Index: 97490 (C4 (Web Text))

Max Activating Token Index: 394