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

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

Neuron 7 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: 3.3318. Min Range: -3.3318

Max Act: 3.3318. Min Act: -0.1700

Data Index: 181855 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.3161. Min Act: -0.1700

Data Index: 829410 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.2218. Min Act: -0.1700

Data Index: 388918 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.2375. Min Act: -0.1700

Data Index: 193278 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.2061. Min Act: -0.1700

Data Index: 645474 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.1588. Min Act: -0.1700

Data Index: 131372 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.1746. Min Act: -0.1700

Data Index: 1259532 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.1273. Min Act: -0.1700

Data Index: 615294 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.1431. Min Act: -0.1700

Data Index: 1232131 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.1588. Min Act: -0.1700

Data Index: 421774 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.1588. Min Act: -0.1700

Data Index: 576492 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.1273. Min Act: -0.1700

Data Index: 235294 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.1431. Min Act: -0.1700

Data Index: 125546 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.1116. Min Act: -0.1700

Data Index: 1133633 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.1273. Min Act: -0.1700

Data Index: 1096775 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.0643. Min Act: -0.1700

Data Index: 1312724 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.1116. Min Act: -0.1700

Data Index: 83481 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.1116. Min Act: -0.1700

Data Index: 973927 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.1116. Min Act: -0.1700

Data Index: 1114276 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 3.3318. Min Range: -3.3318

Max Act: 3.1116. Min Act: -0.1700

Data Index: 417740 (C4 (Web Text))

Max Activating Token Index: 568