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

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

Neuron 1800 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: 3.6506. Min Range: -3.6506

Max Act: 3.6506. Min Act: -0.1700

Data Index: 651037 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.5566. Min Act: -0.1700

Data Index: 204803 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.4940. Min Act: -0.1700

Data Index: 1185248 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.6193. Min Act: -0.1700

Data Index: 1358379 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.6506. Min Act: -0.1700

Data Index: 1206814 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.6193. Min Act: -0.1700

Data Index: 368660 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.5879. Min Act: -0.1700

Data Index: 361616 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.5253. Min Act: -0.1700

Data Index: 75236 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.4940. Min Act: -0.1700

Data Index: 871583 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.4940. Min Act: -0.1700

Data Index: 1182218 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.4313. Min Act: -0.1700

Data Index: 901628 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.5253. Min Act: -0.1700

Data Index: 228083 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.4940. Min Act: -0.1700

Data Index: 394962 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.3999. Min Act: -0.1700

Data Index: 143171 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.4313. Min Act: -0.1700

Data Index: 630192 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.4940. Min Act: -0.1700

Data Index: 1031933 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.4313. Min Act: -0.1700

Data Index: 464871 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.4626. Min Act: -0.1700

Data Index: 55201 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.4940. Min Act: -0.1700

Data Index: 782444 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 3.6506. Min Range: -3.6506

Max Act: 3.3057. Min Act: -0.1700

Data Index: 875943 (C4 (Web Text))

Max Activating Token Index: 844