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

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

Neuron 1314 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.4300. Min Act: -0.1700

Data Index: 671979 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.3515. Min Act: -0.1700

Data Index: 1382431 (Python Code)

Max Activating Token Index: 508

Text #2

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.3515. Min Act: -0.1700

Data Index: 1626594 (Python Code)

Max Activating Token Index: 599

Text #3

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.1944. Min Act: -0.1700

Data Index: 715624 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0999. Min Act: -0.1700

Data Index: 559467 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0841. Min Act: -0.1700

Data Index: 646547 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0999. Min Act: -0.1700

Data Index: 1441136 (Python Code)

Max Activating Token Index: 105

Text #7

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0999. Min Act: -0.1700

Data Index: 27698 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0683. Min Act: -0.1700

Data Index: 945418 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0683. Min Act: -0.1700

Data Index: 8153 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0683. Min Act: -0.1700

Data Index: 908273 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0683. Min Act: -0.1700

Data Index: 931193 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0526. Min Act: -0.1700

Data Index: 1329198 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0683. Min Act: -0.1700

Data Index: 506824 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0368. Min Act: -0.1700

Data Index: 1075230 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0526. Min Act: -0.1700

Data Index: 373688 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0368. Min Act: -0.1700

Data Index: 185575 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0526. Min Act: -0.1700

Data Index: 1296368 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0368. Min Act: -0.1700

Data Index: 931230 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 3.4300. Min Range: -3.4300

Max Act: 3.0368. Min Act: -0.1700

Data Index: 390139 (C4 (Web Text))

Max Activating Token Index: 293