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

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

Neuron 56 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: 3.9325. Min Range: -3.9325

Max Act: 3.9012. Min Act: -0.1700

Data Index: 761337 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.9012. Min Act: -0.1700

Data Index: 1412164 (Python Code)

Max Activating Token Index: 418

Text #2

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.9325. Min Act: -0.1700

Data Index: 1214150 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.9325. Min Act: -0.1700

Data Index: 289151 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.8699. Min Act: -0.1700

Data Index: 269033 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.8230. Min Act: -0.1700

Data Index: 1449067 (Python Code)

Max Activating Token Index: 266

Text #6

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.8230. Min Act: -0.1700

Data Index: 19855 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.8387. Min Act: -0.1700

Data Index: 166347 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.8230. Min Act: -0.1700

Data Index: 1115204 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.8230. Min Act: -0.1700

Data Index: 309250 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.7917. Min Act: -0.1700

Data Index: 247278 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.8074. Min Act: -0.1700

Data Index: 769719 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.7917. Min Act: -0.1700

Data Index: 616767 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.7448. Min Act: -0.1700

Data Index: 1135123 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.7448. Min Act: -0.1700

Data Index: 49408 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.7761. Min Act: -0.1700

Data Index: 657550 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.7604. Min Act: -0.1700

Data Index: 939239 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.7604. Min Act: -0.1700

Data Index: 301625 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.7448. Min Act: -0.1700

Data Index: 652951 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 3.9325. Min Range: -3.9325

Max Act: 3.7292. Min Act: -0.1700

Data Index: 712031 (C4 (Web Text))

Max Activating Token Index: 169