Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1774 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.7759. Min Act: -0.1700

Data Index: 541945 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.5568. Min Act: -0.1700

Data Index: 875135 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.5568. Min Act: -0.1700

Data Index: 393736 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.5255. Min Act: -0.1700

Data Index: 1198209 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.5255. Min Act: -0.1700

Data Index: 1164844 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.4628. Min Act: -0.1700

Data Index: 553759 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.4628. Min Act: -0.1700

Data Index: 1196027 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.4628. Min Act: -0.1700

Data Index: 149804 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.4001. Min Act: -0.1700

Data Index: 1131701 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.4314. Min Act: -0.1700

Data Index: 539386 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.3687. Min Act: -0.1700

Data Index: 154289 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.3687. Min Act: -0.1700

Data Index: 330550 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.3373. Min Act: -0.1700

Data Index: 673602 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.3687. Min Act: -0.1700

Data Index: 319917 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.3687. Min Act: -0.1699

Data Index: 617515 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.3059. Min Act: -0.1700

Data Index: 968015 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.3373. Min Act: -0.1700

Data Index: 927948 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.3373. Min Act: -0.1700

Data Index: 729606 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.3059. Min Act: -0.1700

Data Index: 418021 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 3.7759. Min Range: -3.7759

Max Act: 3.3373. Min Act: -0.1700

Data Index: 477182 (C4 (Web Text))

Max Activating Token Index: 151