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

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

Neuron 1598 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: 1.7745. Min Range: -1.7745

Max Act: 1.7745. Min Act: -0.0001

Data Index: 1113899 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 1.7745. Min Range: -1.7745

Max Act: 1.3883. Min Act: -0.0001

Data Index: 569791 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 1.7745. Min Range: -1.7745

Max Act: 1.1051. Min Act: -0.0001

Data Index: 1540204 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 1.7745. Min Range: -1.7745

Max Act: 1.0906. Min Act: -0.0001

Data Index: 127508 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 1.7745. Min Range: -1.7745

Max Act: 1.0929. Min Act: -0.0001

Data Index: 1565859 (Python Code)

Max Activating Token Index: 43

Text #5

Max Range: 1.7745. Min Range: -1.7745

Max Act: 0.9826. Min Act: -0.0001

Data Index: 374865 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 1.7745. Min Range: -1.7745

Max Act: 1.0704. Min Act: -0.0001

Data Index: 1491642 (Python Code)

Max Activating Token Index: 250

Text #7

Max Range: 1.7745. Min Range: -1.7745

Max Act: 1.0332. Min Act: -0.0001

Data Index: 146153 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 1.7745. Min Range: -1.7745

Max Act: 1.0329. Min Act: -0.0001

Data Index: 1316014 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 1.7745. Min Range: -1.7745

Max Act: 0.9679. Min Act: -0.0001

Data Index: 1352823 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 1.7745. Min Range: -1.7745

Max Act: 0.9598. Min Act: -0.0001

Data Index: 1043929 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 1.7745. Min Range: -1.7745

Max Act: 1.0304. Min Act: -0.0001

Data Index: 1271120 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 1.7745. Min Range: -1.7745

Max Act: 0.9913. Min Act: -0.0001

Data Index: 147541 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 1.7745. Min Range: -1.7745

Max Act: 0.9396. Min Act: -0.0001

Data Index: 353936 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 1.7745. Min Range: -1.7745

Max Act: 0.9044. Min Act: -0.0001

Data Index: 280763 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 1.7745. Min Range: -1.7745

Max Act: 0.9316. Min Act: -0.0001

Data Index: 1188774 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 1.7745. Min Range: -1.7745

Max Act: 0.9291. Min Act: -0.0001

Data Index: 1237974 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 1.7745. Min Range: -1.7745

Max Act: 0.9738. Min Act: -0.0001

Data Index: 190737 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 1.7745. Min Range: -1.7745

Max Act: 0.9314. Min Act: -0.0001

Data Index: 1099952 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 1.7745. Min Range: -1.7745

Max Act: 0.9088. Min Act: -0.0001

Data Index: 620445 (C4 (Web Text))

Max Activating Token Index: 613