Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 980 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.3451. Min Act: -0.1700

Data Index: 137489 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.3138. Min Act: -0.1700

Data Index: 721406 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.2826. Min Act: -0.1700

Data Index: 1198776 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.2201. Min Act: -0.1700

Data Index: 91613 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.2513. Min Act: -0.1700

Data Index: 867693 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.1888. Min Act: -0.1700

Data Index: 1252196 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.2201. Min Act: -0.1700

Data Index: 173130 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.2513. Min Act: -0.1700

Data Index: 1183449 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.2513. Min Act: -0.1700

Data Index: 675044 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.1576. Min Act: -0.1700

Data Index: 912718 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.1888. Min Act: -0.1700

Data Index: 1072119 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.1263. Min Act: -0.1700

Data Index: 108126 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.2201. Min Act: -0.1700

Data Index: 1010782 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.1263. Min Act: -0.1700

Data Index: 1265597 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.1576. Min Act: -0.1700

Data Index: 1325956 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.1576. Min Act: -0.1700

Data Index: 1223727 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.0951. Min Act: -0.1700

Data Index: 109311 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.0638. Min Act: -0.1700

Data Index: 142595 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.0951. Min Act: -0.1700

Data Index: 777787 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 5.3451. Min Range: -5.3451

Max Act: 5.1263. Min Act: -0.1700

Data Index: 781495 (C4 (Web Text))

Max Activating Token Index: 540