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

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

Neuron 1941 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: 5.4972. Min Range: -5.4972

Max Act: 5.4972. Min Act: -0.1700

Data Index: 252636 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.4503. Min Act: -0.1700

Data Index: 1227322 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.3878. Min Act: -0.1700

Data Index: 142337 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.2628. Min Act: -0.1700

Data Index: 250273 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.3097. Min Act: -0.1700

Data Index: 452230 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.2159. Min Act: -0.1700

Data Index: 1136379 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.2628. Min Act: -0.1700

Data Index: 379655 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.2316. Min Act: -0.1700

Data Index: 887773 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.2941. Min Act: -0.1700

Data Index: 1024067 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.2316. Min Act: -0.1700

Data Index: 1060397 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.0909. Min Act: -0.1700

Data Index: 12198 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.2316. Min Act: -0.1700

Data Index: 325100 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.2628. Min Act: -0.1700

Data Index: 440426 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.2472. Min Act: -0.1700

Data Index: 1340098 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.1378. Min Act: -0.1700

Data Index: 1224017 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.2003. Min Act: -0.1700

Data Index: 1353069 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.1691. Min Act: -0.1700

Data Index: 462499 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.2003. Min Act: -0.1700

Data Index: 62094 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.1847. Min Act: -0.1700

Data Index: 1309076 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 5.4972. Min Range: -5.4972

Max Act: 5.2316. Min Act: -0.1700

Data Index: 701912 (C4 (Web Text))

Max Activating Token Index: 445