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

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

Neuron 325 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.7590. Min Act: -0.0002

Data Index: 934548 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.6743. Min Act: -0.0001

Data Index: 709410 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.2549. Min Act: -0.0002

Data Index: 609112 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.3908. Min Act: -0.0001

Data Index: 1035993 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.3338. Min Act: -0.0001

Data Index: 349083 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.3640. Min Act: -0.0001

Data Index: 18836 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.3310. Min Act: -0.0001

Data Index: 1343508 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.2484. Min Act: -0.0001

Data Index: 770365 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.1738. Min Act: -0.0001

Data Index: 879283 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.3603. Min Act: -0.0001

Data Index: 57209 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.2238. Min Act: -0.0001

Data Index: 1211089 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.3325. Min Act: -0.0001

Data Index: 797236 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.2374. Min Act: -0.0001

Data Index: 69212 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.1086. Min Act: -0.0001

Data Index: 358705 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.2039. Min Act: -0.0001

Data Index: 102373 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.0345. Min Act: -0.0001

Data Index: 107229 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.1949. Min Act: -0.0001

Data Index: 519545 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.1449. Min Act: -0.0001

Data Index: 1147200 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.1067. Min Act: -0.0001

Data Index: 713767 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 1.7590. Min Range: -1.7590

Max Act: 1.2002. Min Act: -0.0001

Data Index: 237399 (C4 (Web Text))

Max Activating Token Index: 15