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

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

Neuron 1285 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: 3.9322. Min Range: -3.9322

Max Act: 3.9322. Min Act: -0.1700

Data Index: 693959 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.5880. Min Act: -0.1700

Data Index: 77685 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.6193. Min Act: -0.1700

Data Index: 746484 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.5253. Min Act: -0.1700

Data Index: 826253 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.4470. Min Act: -0.1700

Data Index: 65936 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.4470. Min Act: -0.1700

Data Index: 465707 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.3686. Min Act: -0.1700

Data Index: 55926 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.4156. Min Act: -0.1700

Data Index: 780733 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.3686. Min Act: -0.1700

Data Index: 590108 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.4156. Min Act: -0.1700

Data Index: 168998 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.4156. Min Act: -0.1700

Data Index: 722705 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.3215. Min Act: -0.1700

Data Index: 420807 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.3215. Min Act: -0.1700

Data Index: 1349095 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.2744. Min Act: -0.1700

Data Index: 907862 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.3215. Min Act: -0.1700

Data Index: 801308 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.3058. Min Act: -0.1700

Data Index: 952801 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.3058. Min Act: -0.1700

Data Index: 55859 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.2901. Min Act: -0.1700

Data Index: 252820 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.3058. Min Act: -0.1700

Data Index: 520407 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 3.9322. Min Range: -3.9322

Max Act: 3.2901. Min Act: -0.1700

Data Index: 217848 (C4 (Web Text))

Max Activating Token Index: 635