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

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

Neuron 199 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2497. Min Range: -4.2497

Max Act: 4.2497. Min Act: -0.1700

Data Index: 264714 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 4.2497. Min Range: -4.2497

Max Act: 4.1560. Min Act: -0.1700

Data Index: 845293 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 4.2497. Min Range: -4.2497

Max Act: 4.0935. Min Act: -0.1700

Data Index: 883964 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.9997. Min Act: -0.1700

Data Index: 1072924 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.9371. Min Act: -0.1700

Data Index: 879642 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.9371. Min Act: -0.1700

Data Index: 1299275 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.9371. Min Act: -0.1700

Data Index: 144332 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.9371. Min Act: -0.1700

Data Index: 147210 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.9059. Min Act: -0.1700

Data Index: 182432 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.9684. Min Act: -0.1700

Data Index: 872722 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.9059. Min Act: -0.1700

Data Index: 892937 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.8746. Min Act: -0.1700

Data Index: 784993 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.8746. Min Act: -0.1700

Data Index: 429867 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.8746. Min Act: -0.1700

Data Index: 800598 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.8120. Min Act: -0.1700

Data Index: 81882 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.8746. Min Act: -0.1700

Data Index: 264985 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.8433. Min Act: -0.1700

Data Index: 112905 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.8746. Min Act: -0.1700

Data Index: 179436 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.8120. Min Act: -0.1700

Data Index: 868619 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 4.2497. Min Range: -4.2497

Max Act: 3.8120. Min Act: -0.1700

Data Index: 613062 (C4 (Web Text))

Max Activating Token Index: 29