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

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

Neuron 2046 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3257. Min Range: -5.3257

Max Act: 5.3257. Min Act: -0.1700

Data Index: 936690 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 5.3257. Min Range: -5.3257

Max Act: 5.0444. Min Act: -0.1700

Data Index: 1296767 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 5.3257. Min Range: -5.3257

Max Act: 5.1069. Min Act: -0.1700

Data Index: 820534 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 5.3257. Min Range: -5.3257

Max Act: 5.0444. Min Act: -0.1700

Data Index: 393752 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 5.3257. Min Range: -5.3257

Max Act: 5.0444. Min Act: -0.1700

Data Index: 1252128 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 5.3257. Min Range: -5.3257

Max Act: 5.1069. Min Act: -0.1700

Data Index: 987090 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 5.3257. Min Range: -5.3257

Max Act: 5.0132. Min Act: -0.1700

Data Index: 304084 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 5.3257. Min Range: -5.3257

Max Act: 4.9819. Min Act: -0.1700

Data Index: 1349930 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 5.3257. Min Range: -5.3257

Max Act: 4.9819. Min Act: -0.1700

Data Index: 738549 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 5.3257. Min Range: -5.3257

Max Act: 4.9819. Min Act: -0.1700

Data Index: 136317 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 5.3257. Min Range: -5.3257

Max Act: 4.9507. Min Act: -0.1700

Data Index: 846602 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 5.3257. Min Range: -5.3257

Max Act: 4.9819. Min Act: -0.1700

Data Index: 363521 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 5.3257. Min Range: -5.3257

Max Act: 4.9819. Min Act: -0.1700

Data Index: 234935 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 5.3257. Min Range: -5.3257

Max Act: 4.9819. Min Act: -0.1700

Data Index: 112966 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 5.3257. Min Range: -5.3257

Max Act: 4.9507. Min Act: -0.1700

Data Index: 324922 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 5.3257. Min Range: -5.3257

Max Act: 4.9819. Min Act: -0.1700

Data Index: 1248462 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 5.3257. Min Range: -5.3257

Max Act: 4.9507. Min Act: -0.1700

Data Index: 965810 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 5.3257. Min Range: -5.3257

Max Act: 4.9194. Min Act: -0.1700

Data Index: 1115250 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 5.3257. Min Range: -5.3257

Max Act: 4.9507. Min Act: -0.1700

Data Index: 325504 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 5.3257. Min Range: -5.3257

Max Act: 4.9507. Min Act: -0.1700

Data Index: 100314 (C4 (Web Text))

Max Activating Token Index: 732