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

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

Neuron 671 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: 3.1978. Min Range: -3.1978

Max Act: 3.1978. Min Act: -0.1700

Data Index: 404883 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 3.1978. Min Range: -3.1978

Max Act: 3.1663. Min Act: -0.1700

Data Index: 833714 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 3.1978. Min Range: -3.1978

Max Act: 3.0718. Min Act: -0.1700

Data Index: 358623 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 3.1978. Min Range: -3.1978

Max Act: 3.0718. Min Act: -0.1700

Data Index: 1247252 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 3.1978. Min Range: -3.1978

Max Act: 3.0402. Min Act: -0.1700

Data Index: 724464 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 3.1978. Min Range: -3.1978

Max Act: 3.0560. Min Act: -0.1700

Data Index: 166652 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 3.1978. Min Range: -3.1978

Max Act: 3.0402. Min Act: -0.1700

Data Index: 652293 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 3.1978. Min Range: -3.1978

Max Act: 3.0402. Min Act: -0.1700

Data Index: 544354 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 3.1978. Min Range: -3.1978

Max Act: 3.0086. Min Act: -0.1700

Data Index: 1284162 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 3.1978. Min Range: -3.1978

Max Act: 2.9928. Min Act: -0.1700

Data Index: 567271 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 3.1978. Min Range: -3.1978

Max Act: 2.9928. Min Act: -0.1700

Data Index: 787140 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 3.1978. Min Range: -3.1978

Max Act: 3.0086. Min Act: -0.1700

Data Index: 86613 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 3.1978. Min Range: -3.1978

Max Act: 2.9928. Min Act: -0.1700

Data Index: 456758 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 3.1978. Min Range: -3.1978

Max Act: 2.9770. Min Act: -0.1700

Data Index: 193194 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 3.1978. Min Range: -3.1978

Max Act: 2.9770. Min Act: -0.1700

Data Index: 847297 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 3.1978. Min Range: -3.1978

Max Act: 2.9770. Min Act: -0.1700

Data Index: 587244 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 3.1978. Min Range: -3.1978

Max Act: 2.9612. Min Act: -0.1700

Data Index: 471081 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 3.1978. Min Range: -3.1978

Max Act: 2.9770. Min Act: -0.1700

Data Index: 744398 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 3.1978. Min Range: -3.1978

Max Act: 2.9770. Min Act: -0.1700

Data Index: 878850 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 3.1978. Min Range: -3.1978

Max Act: 2.9453. Min Act: -0.1700

Data Index: 77428 (C4 (Web Text))

Max Activating Token Index: 874