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

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

Neuron 1562 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: 5.2716. Min Range: -5.2716

Max Act: 5.2716. Min Act: -0.1700

Data Index: 41144 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 5.2716. Min Range: -5.2716

Max Act: 5.2091. Min Act: -0.1700

Data Index: 720189 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 5.2716. Min Range: -5.2716

Max Act: 5.1153. Min Act: -0.1700

Data Index: 966587 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.9591. Min Act: -0.1700

Data Index: 1161010 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.9903. Min Act: -0.1700

Data Index: 672675 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.9591. Min Act: -0.1700

Data Index: 611156 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.9278. Min Act: -0.1700

Data Index: 70850 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.9591. Min Act: -0.1700

Data Index: 1192425 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.8653. Min Act: -0.1700

Data Index: 439029 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.8966. Min Act: -0.1700

Data Index: 927653 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.8966. Min Act: -0.1700

Data Index: 372881 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.8653. Min Act: -0.1700

Data Index: 1258094 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.8966. Min Act: -0.1700

Data Index: 984418 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.8966. Min Act: -0.1700

Data Index: 412844 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.9278. Min Act: -0.1700

Data Index: 397944 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.8966. Min Act: -0.1700

Data Index: 265583 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.8653. Min Act: -0.1700

Data Index: 608336 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.8341. Min Act: -0.1700

Data Index: 897664 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.8341. Min Act: -0.1700

Data Index: 360239 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 5.2716. Min Range: -5.2716

Max Act: 4.8341. Min Act: -0.1700

Data Index: 177823 (C4 (Web Text))

Max Activating Token Index: 891