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

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

Neuron 2013 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7802. Min Act: -0.1700

Data Index: 854367 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7333. Min Act: -0.1700

Data Index: 59785 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7333. Min Act: -0.1700

Data Index: 406765 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7333. Min Act: -0.1700

Data Index: 564481 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7490. Min Act: -0.1700

Data Index: 644392 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7333. Min Act: -0.1700

Data Index: 39863 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7020. Min Act: -0.1700

Data Index: 127600 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7177. Min Act: -0.1700

Data Index: 1195306 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7020. Min Act: -0.1700

Data Index: 108319 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7177. Min Act: -0.1700

Data Index: 806090 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7020. Min Act: -0.1700

Data Index: 465859 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7020. Min Act: -0.1700

Data Index: 242770 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7020. Min Act: -0.1700

Data Index: 100723 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7020. Min Act: -0.1700

Data Index: 492958 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7020. Min Act: -0.1700

Data Index: 1015387 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.6864. Min Act: -0.1700

Data Index: 466187 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.6864. Min Act: -0.1700

Data Index: 866575 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.6864. Min Act: -0.1700

Data Index: 878579 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7020. Min Act: -0.1700

Data Index: 930466 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 3.7802. Min Range: -3.7802

Max Act: 3.7020. Min Act: -0.1700

Data Index: 1006747 (C4 (Web Text))

Max Activating Token Index: 351