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

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

Neuron 5571 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.7801. Min Act: -0.0001

Data Index: 541760 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5358. Min Act: -0.0001

Data Index: 901739 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5245. Min Act: -0.0001

Data Index: 1318704 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5340. Min Act: -0.0001

Data Index: 166505 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5382. Min Act: -0.0001

Data Index: 79540 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5276. Min Act: -0.0001

Data Index: 469034 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5096. Min Act: -0.0001

Data Index: 7468 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5068. Min Act: -0.0001

Data Index: 185065 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.4743. Min Act: -0.0001

Data Index: 11521 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5353. Min Act: -0.0001

Data Index: 654619 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5161. Min Act: -0.0001

Data Index: 606498 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.4953. Min Act: -0.0001

Data Index: 209218 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5058. Min Act: -0.0001

Data Index: 215680 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5096. Min Act: -0.0001

Data Index: 230714 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.4877. Min Act: -0.0001

Data Index: 21907 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.4979. Min Act: -0.0001

Data Index: 172331 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.4856. Min Act: -0.0001

Data Index: 1309871 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5326. Min Act: -0.0001

Data Index: 1077292 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5137. Min Act: -0.0001

Data Index: 265777 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.4908. Min Act: -0.0001

Data Index: 1056822 (C4 (Web Text))

Max Activating Token Index: 705