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

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

Neuron 440 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: 0.8214. Min Range: -0.8214

Max Act: 0.8202. Min Act: -0.0000

Data Index: 656509 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.7720. Min Act: -0.0000

Data Index: 586476 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.7482. Min Act: -0.0000

Data Index: 871255 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6930. Min Act: -0.0000

Data Index: 422230 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1247773 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.7962. Min Act: -0.0000

Data Index: 569703 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6811. Min Act: -0.0000

Data Index: 219375 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6888. Min Act: -0.0000

Data Index: 186335 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6682. Min Act: -0.0000

Data Index: 140059 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6936. Min Act: -0.0000

Data Index: 973607 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6562. Min Act: -0.0000

Data Index: 437684 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1021899 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1284165 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6782. Min Act: -0.0000

Data Index: 771422 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1152705 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6150. Min Act: -0.0000

Data Index: 128534 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1127077 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6280. Min Act: -0.0000

Data Index: 447434 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6721. Min Act: -0.0000

Data Index: 783475 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1227009 (C4 (Web Text))

Max Activating Token Index: 391