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

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

Neuron 1472 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1090. Min Range: -4.1090

Max Act: 4.1090. Min Act: -0.1700

Data Index: 1267923 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.8902. Min Act: -0.1700

Data Index: 674269 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.7964. Min Act: -0.1700

Data Index: 1003022 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.7651. Min Act: -0.1700

Data Index: 419225 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.7338. Min Act: -0.1700

Data Index: 1297363 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.7025. Min Act: -0.1700

Data Index: 1039830 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.7025. Min Act: -0.1700

Data Index: 1032354 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.6712. Min Act: -0.1700

Data Index: 343660 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.6712. Min Act: -0.1700

Data Index: 268283 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.6712. Min Act: -0.1700

Data Index: 280398 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1242013 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.6712. Min Act: -0.1700

Data Index: 869249 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.6399. Min Act: -0.1700

Data Index: 696158 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.6399. Min Act: -0.1700

Data Index: 544285 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.6399. Min Act: -0.1700

Data Index: 54929 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.6399. Min Act: -0.1700

Data Index: 261619 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.6399. Min Act: -0.1699

Data Index: 1030689 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.6086. Min Act: -0.1700

Data Index: 424170 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.5773. Min Act: -0.1700

Data Index: 1060134 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.6086. Min Act: -0.1700

Data Index: 1167313 (C4 (Web Text))

Max Activating Token Index: 411