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

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

Neuron 3765 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1851. Min Range: -1.1851

Max Act: 1.1851. Min Act: -0.0001

Data Index: 1364607 (Python Code)

Max Activating Token Index: 396

Text #1

Max Range: 1.1851. Min Range: -1.1851

Max Act: 1.1474. Min Act: -0.0001

Data Index: 913074 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 1.1851. Min Range: -1.1851

Max Act: 1.1071. Min Act: -0.0001

Data Index: 1159983 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 1.1851. Min Range: -1.1851

Max Act: 1.0895. Min Act: -0.0001

Data Index: 136519 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 1.1851. Min Range: -1.1851

Max Act: 1.0889. Min Act: -0.0001

Data Index: 614094 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 1.1851. Min Range: -1.1851

Max Act: 1.0511. Min Act: -0.0001

Data Index: 794463 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 1.1851. Min Range: -1.1851

Max Act: 1.0649. Min Act: -0.0001

Data Index: 7095 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 1.1851. Min Range: -1.1851

Max Act: 1.0663. Min Act: -0.0001

Data Index: 823574 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 1.1851. Min Range: -1.1851

Max Act: 1.1223. Min Act: -0.0001

Data Index: 18284 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 1.1851. Min Range: -1.1851

Max Act: 1.0183. Min Act: -0.0001

Data Index: 311719 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 1.1851. Min Range: -1.1851

Max Act: 1.0767. Min Act: -0.0001

Data Index: 789892 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 1.1851. Min Range: -1.1851

Max Act: 0.9704. Min Act: -0.0001

Data Index: 491426 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 1.1851. Min Range: -1.1851

Max Act: 1.0370. Min Act: -0.0001

Data Index: 26126 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 1.1851. Min Range: -1.1851

Max Act: 0.9956. Min Act: -0.0001

Data Index: 1112690 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 1.1851. Min Range: -1.1851

Max Act: 1.0008. Min Act: -0.0001

Data Index: 301253 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 1.1851. Min Range: -1.1851

Max Act: 0.9955. Min Act: -0.0001

Data Index: 382820 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 1.1851. Min Range: -1.1851

Max Act: 1.0272. Min Act: -0.0001

Data Index: 1324091 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 1.1851. Min Range: -1.1851

Max Act: 1.0036. Min Act: -0.0001

Data Index: 31386 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 1.1851. Min Range: -1.1851

Max Act: 0.9927. Min Act: -0.0001

Data Index: 727115 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.1851. Min Range: -1.1851

Max Act: 0.9650. Min Act: -0.0001

Data Index: 1280488 (C4 (Web Text))

Max Activating Token Index: 977