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

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

Neuron 196 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: 3.8235. Min Range: -3.8235

Max Act: 3.8235. Min Act: -0.1700

Data Index: 1247905 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.8078. Min Act: -0.1700

Data Index: 770906 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7922. Min Act: -0.1700

Data Index: 84603 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7922. Min Act: -0.1700

Data Index: 259386 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.8078. Min Act: -0.1700

Data Index: 961184 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7765. Min Act: -0.1700

Data Index: 1192083 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7609. Min Act: -0.1700

Data Index: 701755 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7296. Min Act: -0.1700

Data Index: 891990 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7452. Min Act: -0.1700

Data Index: 1095379 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7452. Min Act: -0.1700

Data Index: 324697 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7452. Min Act: -0.1700

Data Index: 513707 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7296. Min Act: -0.1700

Data Index: 372091 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7452. Min Act: -0.1700

Data Index: 229012 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.6983. Min Act: -0.1700

Data Index: 934146 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.6670. Min Act: -0.1700

Data Index: 535016 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7140. Min Act: -0.1700

Data Index: 246531 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7140. Min Act: -0.1700

Data Index: 1198449 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.6827. Min Act: -0.1700

Data Index: 213096 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.6983. Min Act: -0.1700

Data Index: 520455 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7140. Min Act: -0.1700

Data Index: 1210279 (C4 (Web Text))

Max Activating Token Index: 463