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

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

Neuron 291 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.7334. Min Act: -0.1700

Data Index: 1046319 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1142391 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.6082. Min Act: -0.1700

Data Index: 98037 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.5769. Min Act: -0.1700

Data Index: 124162 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.6082. Min Act: -0.1700

Data Index: 861796 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.5769. Min Act: -0.1700

Data Index: 102255 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.5769. Min Act: -0.1700

Data Index: 78634 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.5769. Min Act: -0.1700

Data Index: 976764 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.6082. Min Act: -0.1700

Data Index: 352182 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.5455. Min Act: -0.1700

Data Index: 787078 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.5455. Min Act: -0.1700

Data Index: 464528 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.5455. Min Act: -0.1700

Data Index: 511821 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.5455. Min Act: -0.1700

Data Index: 807138 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.5455. Min Act: -0.1700

Data Index: 985739 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.5142. Min Act: -0.1700

Data Index: 1006691 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.4829. Min Act: -0.1700

Data Index: 594579 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.5455. Min Act: -0.1700

Data Index: 869134 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.4829. Min Act: -0.1700

Data Index: 937430 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.4829. Min Act: -0.1700

Data Index: 34670 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 3.7334. Min Range: -3.7334

Max Act: 3.4829. Min Act: -0.1700

Data Index: 171757 (C4 (Web Text))

Max Activating Token Index: 145