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

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

Neuron 561 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6944. Min Act: -0.1700

Data Index: 546487 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.7257. Min Act: -0.1700

Data Index: 666991 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.7101. Min Act: -0.1700

Data Index: 1351522 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6788. Min Act: -0.1700

Data Index: 45493 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6788. Min Act: -0.1700

Data Index: 801395 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6631. Min Act: -0.1700

Data Index: 416345 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6475. Min Act: -0.1700

Data Index: 79553 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6631. Min Act: -0.1700

Data Index: 56991 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6788. Min Act: -0.1700

Data Index: 240205 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6005. Min Act: -0.1700

Data Index: 1330704 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6475. Min Act: -0.1700

Data Index: 470643 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6788. Min Act: -0.1700

Data Index: 17858 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6318. Min Act: -0.1700

Data Index: 496792 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6475. Min Act: -0.1700

Data Index: 775414 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6318. Min Act: -0.1700

Data Index: 74861 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6162. Min Act: -0.1700

Data Index: 588223 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6162. Min Act: -0.1700

Data Index: 1154435 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6318. Min Act: -0.1700

Data Index: 400512 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6162. Min Act: -0.1700

Data Index: 951003 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6162. Min Act: -0.1700

Data Index: 396974 (C4 (Web Text))

Max Activating Token Index: 308