Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 400 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.2450. Min Range: -4.2450

Max Act: 4.2450. Min Act: -0.1700

Data Index: 556531 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 4.2450. Min Range: -4.2450

Max Act: 4.1825. Min Act: -0.1700

Data Index: 1297278 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 4.2450. Min Range: -4.2450

Max Act: 4.1513. Min Act: -0.1700

Data Index: 85454 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 4.2450. Min Range: -4.2450

Max Act: 4.0887. Min Act: -0.1700

Data Index: 1321401 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 4.2450. Min Range: -4.2450

Max Act: 4.0887. Min Act: -0.1700

Data Index: 1052595 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 4.2450. Min Range: -4.2450

Max Act: 4.0575. Min Act: -0.1700

Data Index: 694866 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 4.2450. Min Range: -4.2450

Max Act: 4.0575. Min Act: -0.1699

Data Index: 1036346 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 4.2450. Min Range: -4.2450

Max Act: 3.9950. Min Act: -0.1700

Data Index: 130031 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 4.2450. Min Range: -4.2450

Max Act: 3.9950. Min Act: -0.1700

Data Index: 218761 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 4.2450. Min Range: -4.2450

Max Act: 3.9637. Min Act: -0.1700

Data Index: 389347 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 4.2450. Min Range: -4.2450

Max Act: 3.9324. Min Act: -0.1700

Data Index: 913159 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 4.2450. Min Range: -4.2450

Max Act: 3.9011. Min Act: -0.1700

Data Index: 1152090 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 4.2450. Min Range: -4.2450

Max Act: 3.9011. Min Act: -0.1700

Data Index: 1279164 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 4.2450. Min Range: -4.2450

Max Act: 3.9324. Min Act: -0.1700

Data Index: 1242725 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 4.2450. Min Range: -4.2450

Max Act: 3.9011. Min Act: -0.1700

Data Index: 1352913 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 4.2450. Min Range: -4.2450

Max Act: 3.9011. Min Act: -0.1700

Data Index: 720838 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 4.2450. Min Range: -4.2450

Max Act: 3.8386. Min Act: -0.1700

Data Index: 513483 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 4.2450. Min Range: -4.2450

Max Act: 3.8699. Min Act: -0.1700

Data Index: 943470 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 4.2450. Min Range: -4.2450

Max Act: 3.8386. Min Act: -0.1700

Data Index: 665675 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 4.2450. Min Range: -4.2450

Max Act: 3.8699. Min Act: -0.1700

Data Index: 567614 (C4 (Web Text))

Max Activating Token Index: 160