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

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

Neuron 4787 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2880. Min Range: -7.2880

Max Act: 6.7558. Min Act: -0.0000

Data Index: 112220 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 7.2880. Min Range: -7.2880

Max Act: 7.2880. Min Act: -0.0000

Data Index: 574185 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 7.2880. Min Range: -7.2880

Max Act: 6.3902. Min Act: -0.0000

Data Index: 1005737 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 7.2880. Min Range: -7.2880

Max Act: 6.8016. Min Act: -0.0000

Data Index: 25625 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 7.2880. Min Range: -7.2880

Max Act: 5.4106. Min Act: -0.0000

Data Index: 1117866 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 7.2880. Min Range: -7.2880

Max Act: 6.1230. Min Act: -0.0000

Data Index: 1152186 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 7.2880. Min Range: -7.2880

Max Act: 5.3059. Min Act: -0.0000

Data Index: 507130 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 7.2880. Min Range: -7.2880

Max Act: 5.6974. Min Act: -0.0000

Data Index: 542179 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 7.2880. Min Range: -7.2880

Max Act: 5.3091. Min Act: -0.0000

Data Index: 1278684 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 7.2880. Min Range: -7.2880

Max Act: 4.8455. Min Act: -0.0000

Data Index: 457062 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 7.2880. Min Range: -7.2880

Max Act: 5.2620. Min Act: -0.0000

Data Index: 628142 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 7.2880. Min Range: -7.2880

Max Act: 4.2027. Min Act: -0.0000

Data Index: 893684 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 7.2880. Min Range: -7.2880

Max Act: 4.2259. Min Act: -0.0000

Data Index: 1346400 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 7.2880. Min Range: -7.2880

Max Act: 3.7617. Min Act: -0.0000

Data Index: 212610 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 7.2880. Min Range: -7.2880

Max Act: 4.0307. Min Act: -0.0000

Data Index: 3557 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 7.2880. Min Range: -7.2880

Max Act: 3.4579. Min Act: -0.0000

Data Index: 1227826 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 7.2880. Min Range: -7.2880

Max Act: 3.8453. Min Act: -0.0000

Data Index: 599697 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 7.2880. Min Range: -7.2880

Max Act: 3.4430. Min Act: -0.0000

Data Index: 314828 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 7.2880. Min Range: -7.2880

Max Act: 3.4903. Min Act: -0.0000

Data Index: 186330 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 7.2880. Min Range: -7.2880

Max Act: 3.9234. Min Act: -0.0000

Data Index: 216426 (C4 (Web Text))

Max Activating Token Index: 68