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

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

Neuron 214 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: 3.8526. Min Range: -3.8526

Max Act: 3.8526. Min Act: -0.1700

Data Index: 987071 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.8526. Min Act: -0.1700

Data Index: 961472 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.8213. Min Act: -0.1700

Data Index: 1222835 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.8213. Min Act: -0.1700

Data Index: 126129 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.8213. Min Act: -0.1700

Data Index: 329635 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.7900. Min Act: -0.1700

Data Index: 1254268 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.7900. Min Act: -0.1700

Data Index: 991434 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.7900. Min Act: -0.1700

Data Index: 232393 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.7900. Min Act: -0.1700

Data Index: 112260 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.7587. Min Act: -0.1700

Data Index: 738092 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.7275. Min Act: -0.1700

Data Index: 786963 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.7587. Min Act: -0.1700

Data Index: 908612 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.7275. Min Act: -0.1700

Data Index: 561356 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.7587. Min Act: -0.1700

Data Index: 714399 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.7587. Min Act: -0.1700

Data Index: 1046483 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.7587. Min Act: -0.1700

Data Index: 92506 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.7275. Min Act: -0.1700

Data Index: 1151652 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.7587. Min Act: -0.1700

Data Index: 733459 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.7587. Min Act: -0.1700

Data Index: 1304333 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 3.8526. Min Range: -3.8526

Max Act: 3.7587. Min Act: -0.1700

Data Index: 1103512 (C4 (Web Text))

Max Activating Token Index: 851