Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 304 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.5534. Min Act: -0.1700

Data Index: 85446 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.5534. Min Act: -0.1700

Data Index: 301080 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.4597. Min Act: -0.1700

Data Index: 500195 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.4597. Min Act: -0.1700

Data Index: 235639 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.4597. Min Act: -0.1700

Data Index: 849193 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.3972. Min Act: -0.1700

Data Index: 62921 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.3972. Min Act: -0.1700

Data Index: 416715 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.4284. Min Act: -0.1700

Data Index: 1025080 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.3972. Min Act: -0.1700

Data Index: 628279 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.3972. Min Act: -0.1700

Data Index: 626152 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.3659. Min Act: -0.1700

Data Index: 591744 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.4284. Min Act: -0.1700

Data Index: 804562 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.3659. Min Act: -0.1700

Data Index: 359459 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.3347. Min Act: -0.1700

Data Index: 27259 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.3659. Min Act: -0.1700

Data Index: 275608 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.3659. Min Act: -0.1700

Data Index: 205897 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.3347. Min Act: -0.1700

Data Index: 756012 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.3659. Min Act: -0.1700

Data Index: 700503 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.3034. Min Act: -0.1700

Data Index: 558680 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 5.5534. Min Range: -5.5534

Max Act: 5.3659. Min Act: -0.1700

Data Index: 753644 (C4 (Web Text))

Max Activating Token Index: 126