Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3205 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2295. Min Range: -3.2295

Max Act: 3.2295. Min Act: -0.0000

Data Index: 172943 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 3.2295. Min Range: -3.2295

Max Act: 2.8111. Min Act: -0.0000

Data Index: 369923 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 3.2295. Min Range: -3.2295

Max Act: 2.2102. Min Act: -0.0000

Data Index: 352448 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.8389. Min Act: -0.0000

Data Index: 1180986 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.7576. Min Act: -0.0000

Data Index: 495869 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.6271. Min Act: -0.0000

Data Index: 676616 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.6727. Min Act: -0.0000

Data Index: 711366 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.6814. Min Act: -0.0000

Data Index: 1145779 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.5695. Min Act: -0.0000

Data Index: 453864 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.1945. Min Act: -0.0000

Data Index: 935340 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.5638. Min Act: -0.0000

Data Index: 1132012 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.4848. Min Act: -0.0000

Data Index: 902477 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.6145. Min Act: -0.0000

Data Index: 107440 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.4972. Min Act: -0.0000

Data Index: 525502 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.4210. Min Act: -0.0000

Data Index: 1078781 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.4164. Min Act: -0.0000

Data Index: 498037 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.4865. Min Act: -0.0000

Data Index: 1087848 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.4964. Min Act: -0.0000

Data Index: 268239 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.4848. Min Act: -0.0000

Data Index: 1308865 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 3.2295. Min Range: -3.2295

Max Act: 1.4383. Min Act: -0.0000

Data Index: 1237566 (C4 (Web Text))

Max Activating Token Index: 715