Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1254 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.8211. Min Act: -0.0001

Data Index: 108279 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6461. Min Act: -0.0001

Data Index: 636987 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6345. Min Act: -0.0001

Data Index: 766374 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6193. Min Act: -0.0001

Data Index: 939571 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5811. Min Act: -0.0001

Data Index: 118034 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5917. Min Act: -0.0001

Data Index: 876046 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5871. Min Act: -0.0001

Data Index: 698984 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5644. Min Act: -0.0001

Data Index: 329335 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5744. Min Act: -0.0001

Data Index: 615345 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5730. Min Act: -0.0001

Data Index: 511938 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5729. Min Act: -0.0001

Data Index: 1071350 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5741. Min Act: -0.0001

Data Index: 345877 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5841. Min Act: -0.0001

Data Index: 896715 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5622. Min Act: -0.0001

Data Index: 32457 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5617. Min Act: -0.0001

Data Index: 523382 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5492. Min Act: -0.0001

Data Index: 763185 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5470. Min Act: -0.0001

Data Index: 791905 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5213. Min Act: -0.0001

Data Index: 1315301 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5198. Min Act: -0.0001

Data Index: 733761 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5413. Min Act: -0.0001

Data Index: 692351 (C4 (Web Text))

Max Activating Token Index: 723