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

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

Neuron 424 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1678. Min Range: -5.1678

Max Act: 5.1522. Min Act: -0.1700

Data Index: 754084 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 5.1678. Min Range: -5.1678

Max Act: 5.1678. Min Act: -0.1700

Data Index: 238888 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 5.1678. Min Range: -5.1678

Max Act: 5.1053. Min Act: -0.1700

Data Index: 586558 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 5.1678. Min Range: -5.1678

Max Act: 5.0897. Min Act: -0.1700

Data Index: 264103 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 5.1678. Min Range: -5.1678

Max Act: 5.0584. Min Act: -0.1700

Data Index: 293050 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 5.1678. Min Range: -5.1678

Max Act: 5.0115. Min Act: -0.1700

Data Index: 73589 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 5.1678. Min Range: -5.1678

Max Act: 4.9490. Min Act: -0.1700

Data Index: 930678 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 5.1678. Min Range: -5.1678

Max Act: 4.9647. Min Act: -0.1700

Data Index: 689518 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 5.1678. Min Range: -5.1678

Max Act: 4.9022. Min Act: -0.1700

Data Index: 353671 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 5.1678. Min Range: -5.1678

Max Act: 4.9959. Min Act: -0.1700

Data Index: 79609 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 5.1678. Min Range: -5.1678

Max Act: 4.9334. Min Act: -0.1700

Data Index: 708394 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 5.1678. Min Range: -5.1678

Max Act: 4.9803. Min Act: -0.1700

Data Index: 846662 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 5.1678. Min Range: -5.1678

Max Act: 4.9334. Min Act: -0.1700

Data Index: 292159 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 5.1678. Min Range: -5.1678

Max Act: 4.9490. Min Act: -0.1700

Data Index: 447930 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 5.1678. Min Range: -5.1678

Max Act: 4.9647. Min Act: -0.1700

Data Index: 733582 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 5.1678. Min Range: -5.1678

Max Act: 4.9959. Min Act: -0.1700

Data Index: 1263105 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 5.1678. Min Range: -5.1678

Max Act: 4.9178. Min Act: -0.1700

Data Index: 303534 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 5.1678. Min Range: -5.1678

Max Act: 4.9178. Min Act: -0.1700

Data Index: 569334 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 5.1678. Min Range: -5.1678

Max Act: 4.8240. Min Act: -0.1700

Data Index: 99656 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 5.1678. Min Range: -5.1678

Max Act: 4.8397. Min Act: -0.1700

Data Index: 762733 (C4 (Web Text))

Max Activating Token Index: 342