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

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

Neuron 692 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.7994. Min Act: -0.1700

Data Index: 1175972 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.7056. Min Act: -0.1700

Data Index: 1264600 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6430. Min Act: -0.1700

Data Index: 626759 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.7056. Min Act: -0.1700

Data Index: 1224149 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6743. Min Act: -0.1699

Data Index: 983837 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.7056. Min Act: -0.1700

Data Index: 484303 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6430. Min Act: -0.1700

Data Index: 797316 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6743. Min Act: -0.1700

Data Index: 1206716 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6430. Min Act: -0.1700

Data Index: 700581 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6117. Min Act: -0.1700

Data Index: 636982 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6430. Min Act: -0.1700

Data Index: 464140 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6430. Min Act: -0.1700

Data Index: 596451 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6743. Min Act: -0.1700

Data Index: 383996 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6430. Min Act: -0.1700

Data Index: 1655 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6430. Min Act: -0.1700

Data Index: 369823 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6430. Min Act: -0.1700

Data Index: 30311 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6430. Min Act: -0.1700

Data Index: 299674 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6430. Min Act: -0.1700

Data Index: 217972 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6743. Min Act: -0.1700

Data Index: 664256 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 3.7994. Min Range: -3.7994

Max Act: 3.6117. Min Act: -0.1700

Data Index: 1171523 (C4 (Web Text))

Max Activating Token Index: 103