Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2435 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.4010. Min Act: -0.0001

Data Index: 294452 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.1234. Min Act: -0.0001

Data Index: 849397 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.4145. Min Act: -0.0001

Data Index: 713710 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.1657. Min Act: -0.0001

Data Index: 21951 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.2751. Min Act: -0.0001

Data Index: 708102 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.1385. Min Act: -0.0001

Data Index: 350956 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.1077. Min Act: -0.0001

Data Index: 642665 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.1308. Min Act: -0.0001

Data Index: 778182 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.1006. Min Act: -0.0001

Data Index: 396486 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.0000. Min Act: -0.0001

Data Index: 1085063 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.0331. Min Act: -0.0001

Data Index: 165580 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.4145. Min Range: -1.4145

Max Act: 0.9664. Min Act: -0.0001

Data Index: 238867 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 1.4145. Min Range: -1.4145

Max Act: 0.9487. Min Act: -0.0001

Data Index: 1216132 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 1.4145. Min Range: -1.4145

Max Act: 0.8593. Min Act: -0.0001

Data Index: 1018859 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 1.4145. Min Range: -1.4145

Max Act: 0.9955. Min Act: -0.0001

Data Index: 131202 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 1.4145. Min Range: -1.4145

Max Act: 0.9306. Min Act: -0.0001

Data Index: 173292 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 1.4145. Min Range: -1.4145

Max Act: 0.8243. Min Act: -0.0001

Data Index: 722489 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 1.4145. Min Range: -1.4145

Max Act: 0.9368. Min Act: -0.0001

Data Index: 782462 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.0526. Min Act: -0.0001

Data Index: 477349 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 1.4145. Min Range: -1.4145

Max Act: 0.9269. Min Act: -0.0001

Data Index: 50040 (C4 (Web Text))

Max Activating Token Index: 794