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

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

Neuron 641 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.5892. Min Act: -0.1700

Data Index: 750725 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.5579. Min Act: -0.1700

Data Index: 356644 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.5579. Min Act: -0.1700

Data Index: 620141 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.4325. Min Act: -0.1700

Data Index: 833365 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.4325. Min Act: -0.1700

Data Index: 173422 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.4325. Min Act: -0.1700

Data Index: 1199395 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.4325. Min Act: -0.1700

Data Index: 1040623 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.4012. Min Act: -0.1700

Data Index: 1071103 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.4012. Min Act: -0.1700

Data Index: 673594 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.3698. Min Act: -0.1700

Data Index: 205913 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.3384. Min Act: -0.1700

Data Index: 1101897 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.3698. Min Act: -0.1700

Data Index: 1206436 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.3384. Min Act: -0.1700

Data Index: 665164 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.3384. Min Act: -0.1700

Data Index: 225134 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.3384. Min Act: -0.1700

Data Index: 1123260 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.3070. Min Act: -0.1700

Data Index: 1334184 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.2756. Min Act: -0.1700

Data Index: 1268356 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.3070. Min Act: -0.1700

Data Index: 841866 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.2756. Min Act: -0.1700

Data Index: 5612 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 3.5892. Min Range: -3.5892

Max Act: 3.2127. Min Act: -0.1700

Data Index: 207762 (C4 (Web Text))

Max Activating Token Index: 595