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

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

Neuron 351 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: 3.2778. Min Range: -3.2778

Max Act: 3.2778. Min Act: -0.1700

Data Index: 82513 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.2621. Min Act: -0.1700

Data Index: 529325 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.2778. Min Act: -0.1700

Data Index: 242235 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.2621. Min Act: -0.1700

Data Index: 1224548 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.2621. Min Act: -0.1696

Data Index: 1254676 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.2621. Min Act: -0.1700

Data Index: 1332715 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.2149. Min Act: -0.1699

Data Index: 172411 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.2149. Min Act: -0.1700

Data Index: 286951 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.2149. Min Act: -0.1700

Data Index: 572963 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.1992. Min Act: -0.1700

Data Index: 195780 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.2149. Min Act: -0.1700

Data Index: 773982 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.2149. Min Act: -0.1700

Data Index: 1175931 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.1992. Min Act: -0.1700

Data Index: 1172586 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.1992. Min Act: -0.1700

Data Index: 622891 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.1520. Min Act: -0.1700

Data Index: 717565 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.1835. Min Act: -0.1700

Data Index: 632150 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.1677. Min Act: -0.1700

Data Index: 585346 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.1677. Min Act: -0.1700

Data Index: 330284 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.1677. Min Act: -0.1700

Data Index: 831820 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 3.2778. Min Range: -3.2778

Max Act: 3.1835. Min Act: -0.1680

Data Index: 29420 (C4 (Web Text))

Max Activating Token Index: 477