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

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

Neuron 1650 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.9251. Min Act: -0.0000

Data Index: 1611554 (Python Code)

Max Activating Token Index: 546

Text #1

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.7721. Min Act: -0.0000

Data Index: 597515 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.8413. Min Act: -0.0000

Data Index: 1428692 (Python Code)

Max Activating Token Index: 783

Text #3

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.7511. Min Act: -0.0000

Data Index: 1506506 (Python Code)

Max Activating Token Index: 377

Text #4

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.7035. Min Act: -0.0000

Data Index: 1097316 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.6937. Min Act: -0.0000

Data Index: 416327 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.6913. Min Act: -0.0000

Data Index: 359185 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.6350. Min Act: -0.0000

Data Index: 738065 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.6209. Min Act: -0.0000

Data Index: 184816 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.5754. Min Act: -0.0000

Data Index: 1112390 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.5700. Min Act: -0.0000

Data Index: 509922 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.5538. Min Act: -0.0000

Data Index: 1105227 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.5385. Min Act: -0.0000

Data Index: 947589 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.5140. Min Act: -0.0000

Data Index: 223973 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.5164. Min Act: -0.0000

Data Index: 1005809 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.4287. Min Act: -0.0000

Data Index: 644153 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.4901. Min Act: -0.0000

Data Index: 326757 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.3352. Min Act: -0.0000

Data Index: 1032570 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.4803. Min Act: -0.0000

Data Index: 984968 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 1.9251. Min Range: -1.9251

Max Act: 1.4739. Min Act: -0.0000

Data Index: 1000576 (C4 (Web Text))

Max Activating Token Index: 569