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

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

Neuron 5444 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.6412. Min Act: -0.0000

Data Index: 145560 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.7728. Min Act: -0.0000

Data Index: 401294 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.5767. Min Act: -0.0000

Data Index: 1201537 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.6862. Min Act: -0.0000

Data Index: 994292 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.5993. Min Act: -0.0000

Data Index: 1025442 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.5290. Min Act: -0.0000

Data Index: 24925 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.5261. Min Act: -0.0000

Data Index: 1114714 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.5181. Min Act: -0.0000

Data Index: 658305 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.5080. Min Act: -0.0000

Data Index: 1226921 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.4728. Min Act: -0.0000

Data Index: 768307 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.5078. Min Act: -0.0000

Data Index: 161763 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.4867. Min Act: -0.0000

Data Index: 917098 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.4975. Min Act: -0.0000

Data Index: 527503 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.4706. Min Act: -0.0000

Data Index: 1279400 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.4760. Min Act: -0.0000

Data Index: 668899 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.4174. Min Act: -0.0000

Data Index: 1221625 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.4403. Min Act: -0.0000

Data Index: 796437 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.4438. Min Act: -0.0000

Data Index: 967244 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.4430. Min Act: -0.0000

Data Index: 158783 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.4281. Min Act: -0.0000

Data Index: 42701 (C4 (Web Text))

Max Activating Token Index: 715