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

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

Neuron 1134 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.9737. Min Act: -0.1700

Data Index: 819192 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.8487. Min Act: -0.1700

Data Index: 1290686 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 5.0362. Min Range: -5.0362

Max Act: 5.0049. Min Act: -0.1700

Data Index: 231400 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 5.0362. Min Range: -5.0362

Max Act: 5.0362. Min Act: -0.1700

Data Index: 824771 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.9112. Min Act: -0.1700

Data Index: 915995 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.8487. Min Act: -0.1700

Data Index: 977909 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.8487. Min Act: -0.1700

Data Index: 1277770 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.8487. Min Act: -0.1700

Data Index: 1333700 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.8487. Min Act: -0.1700

Data Index: 241988 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.8487. Min Act: -0.1700

Data Index: 701570 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.8799. Min Act: -0.1700

Data Index: 434040 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.9424. Min Act: -0.1700

Data Index: 248611 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.8487. Min Act: -0.1700

Data Index: 486290 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.7862. Min Act: -0.1700

Data Index: 497426 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.8487. Min Act: -0.1700

Data Index: 295739 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.8174. Min Act: -0.1700

Data Index: 1328218 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.7862. Min Act: -0.1700

Data Index: 935413 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.8487. Min Act: -0.1700

Data Index: 795025 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.7549. Min Act: -0.1700

Data Index: 590217 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 5.0362. Min Range: -5.0362

Max Act: 4.8174. Min Act: -0.1700

Data Index: 560577 (C4 (Web Text))

Max Activating Token Index: 781