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

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

Neuron 2032 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: 5.3378. Min Range: -5.3378

Max Act: 5.3378. Min Act: -0.1700

Data Index: 1250642 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.1815. Min Act: -0.1698

Data Index: 1206535 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.0878. Min Act: -0.1700

Data Index: 4858 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.0565. Min Act: -0.1700

Data Index: 502177 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.0253. Min Act: -0.1700

Data Index: 1317189 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 5.3378. Min Range: -5.3378

Max Act: 4.9628. Min Act: -0.1700

Data Index: 176172 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 5.3378. Min Range: -5.3378

Max Act: 4.9003. Min Act: -0.1700

Data Index: 1232192 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 5.3378. Min Range: -5.3378

Max Act: 4.8690. Min Act: -0.1669

Data Index: 426846 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 5.3378. Min Range: -5.3378

Max Act: 4.8378. Min Act: -0.1700

Data Index: 640990 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 5.3378. Min Range: -5.3378

Max Act: 4.8378. Min Act: -0.1700

Data Index: 1105329 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 5.3378. Min Range: -5.3378

Max Act: 4.7128. Min Act: -0.1700

Data Index: 380156 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 5.3378. Min Range: -5.3378

Max Act: 4.7128. Min Act: -0.1700

Data Index: 245395 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 5.3378. Min Range: -5.3378

Max Act: 4.7440. Min Act: -0.1700

Data Index: 562237 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 5.3378. Min Range: -5.3378

Max Act: 4.7128. Min Act: -0.1700

Data Index: 1032346 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 5.3378. Min Range: -5.3378

Max Act: 4.7440. Min Act: -0.1700

Data Index: 70424 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 5.3378. Min Range: -5.3378

Max Act: 4.6503. Min Act: -0.1700

Data Index: 821878 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 5.3378. Min Range: -5.3378

Max Act: 4.6815. Min Act: -0.1700

Data Index: 921573 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 5.3378. Min Range: -5.3378

Max Act: 4.6815. Min Act: -0.1700

Data Index: 1046506 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 5.3378. Min Range: -5.3378

Max Act: 4.6815. Min Act: -0.1700

Data Index: 358840 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 5.3378. Min Range: -5.3378

Max Act: 4.6815. Min Act: -0.1700

Data Index: 1302379 (C4 (Web Text))

Max Activating Token Index: 383