Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1341 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.7603. Min Act: -0.1700

Data Index: 1270964 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.5416. Min Act: -0.1700

Data Index: 98343 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.4791. Min Act: -0.1700

Data Index: 919602 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.4791. Min Act: -0.1700

Data Index: 555450 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.4478. Min Act: -0.1700

Data Index: 60696 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.3853. Min Act: -0.1700

Data Index: 267419 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.3541. Min Act: -0.1700

Data Index: 236805 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.4166. Min Act: -0.1700

Data Index: 432409 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.3853. Min Act: -0.1700

Data Index: 606428 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.3541. Min Act: -0.1700

Data Index: 670002 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.3228. Min Act: -0.1700

Data Index: 1172444 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.2916. Min Act: -0.1700

Data Index: 934981 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.3853. Min Act: -0.1700

Data Index: 1096901 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.3228. Min Act: -0.1700

Data Index: 506443 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.1978. Min Act: -0.1700

Data Index: 974719 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.3853. Min Act: -0.1700

Data Index: 121212 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.2916. Min Act: -0.1700

Data Index: 58832 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.3541. Min Act: -0.1700

Data Index: 1141922 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.3853. Min Act: -0.1700

Data Index: 731741 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 5.7603. Min Range: -5.7603

Max Act: 5.2916. Min Act: -0.1700

Data Index: 81335 (C4 (Web Text))

Max Activating Token Index: 559