Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 417 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.8143. Min Range: -5.8143

Max Act: 5.8143. Min Act: -0.1700

Data Index: 1268769 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 5.8143. Min Range: -5.8143

Max Act: 5.4237. Min Act: -0.1700

Data Index: 808013 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 5.8143. Min Range: -5.8143

Max Act: 5.2205. Min Act: -0.1700

Data Index: 554729 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 5.8143. Min Range: -5.8143

Max Act: 5.1424. Min Act: -0.1700

Data Index: 1179889 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 5.8143. Min Range: -5.8143

Max Act: 4.9862. Min Act: -0.1700

Data Index: 970328 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 5.8143. Min Range: -5.8143

Max Act: 5.0487. Min Act: -0.1700

Data Index: 372569 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 5.8143. Min Range: -5.8143

Max Act: 4.9862. Min Act: -0.1700

Data Index: 1310760 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 5.8143. Min Range: -5.8143

Max Act: 4.9862. Min Act: -0.1700

Data Index: 914135 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 5.8143. Min Range: -5.8143

Max Act: 4.9080. Min Act: -0.1700

Data Index: 975706 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 5.8143. Min Range: -5.8143

Max Act: 4.9705. Min Act: -0.1700

Data Index: 984966 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 5.8143. Min Range: -5.8143

Max Act: 4.8612. Min Act: -0.1700

Data Index: 1248395 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 5.8143. Min Range: -5.8143

Max Act: 4.9549. Min Act: -0.1700

Data Index: 37435 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 5.8143. Min Range: -5.8143

Max Act: 4.9080. Min Act: -0.1700

Data Index: 315637 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 5.8143. Min Range: -5.8143

Max Act: 4.8299. Min Act: -0.1700

Data Index: 266363 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 5.8143. Min Range: -5.8143

Max Act: 4.9237. Min Act: -0.1700

Data Index: 584917 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 5.8143. Min Range: -5.8143

Max Act: 5.0018. Min Act: -0.1700

Data Index: 977974 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 5.8143. Min Range: -5.8143

Max Act: 4.8455. Min Act: -0.1700

Data Index: 1233809 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 5.8143. Min Range: -5.8143

Max Act: 4.9705. Min Act: -0.1700

Data Index: 480258 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 5.8143. Min Range: -5.8143

Max Act: 4.8924. Min Act: -0.1700

Data Index: 690001 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 5.8143. Min Range: -5.8143

Max Act: 4.8924. Min Act: -0.1700

Data Index: 14845 (C4 (Web Text))

Max Activating Token Index: 1010