Model: GELU Model: 3 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-3l')

Text #0

Max Range: 3.2680. Min Range: -3.2680

Max Act: 3.2680. Min Act: -0.1700

Data Index: 965565 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 3.2680. Min Range: -3.2680

Max Act: 3.2209. Min Act: -0.1700

Data Index: 1322873 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 3.2680. Min Range: -3.2680

Max Act: 3.1737. Min Act: -0.1700

Data Index: 499024 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 3.2680. Min Range: -3.2680

Max Act: 3.1422. Min Act: -0.1700

Data Index: 989062 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 3.2680. Min Range: -3.2680

Max Act: 3.1422. Min Act: -0.1700

Data Index: 1308773 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 3.2680. Min Range: -3.2680

Max Act: 3.0476. Min Act: -0.1700

Data Index: 156401 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 3.2680. Min Range: -3.2680

Max Act: 3.0476. Min Act: -0.1700

Data Index: 648768 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 3.2680. Min Range: -3.2680

Max Act: 3.0476. Min Act: -0.1700

Data Index: 384860 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 3.2680. Min Range: -3.2680

Max Act: 3.0002. Min Act: -0.1700

Data Index: 515143 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 3.2680. Min Range: -3.2680

Max Act: 3.0318. Min Act: -0.1700

Data Index: 318492 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 3.2680. Min Range: -3.2680

Max Act: 3.0318. Min Act: -0.1700

Data Index: 852046 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 3.2680. Min Range: -3.2680

Max Act: 3.0318. Min Act: -0.1700

Data Index: 569556 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 3.2680. Min Range: -3.2680

Max Act: 3.0160. Min Act: -0.1700

Data Index: 80112 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 3.2680. Min Range: -3.2680

Max Act: 3.0160. Min Act: -0.1700

Data Index: 78074 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 3.2680. Min Range: -3.2680

Max Act: 3.0318. Min Act: -0.1700

Data Index: 12591 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 3.2680. Min Range: -3.2680

Max Act: 2.9685. Min Act: -0.1700

Data Index: 60274 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 3.2680. Min Range: -3.2680

Max Act: 2.9527. Min Act: -0.1700

Data Index: 1192972 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 3.2680. Min Range: -3.2680

Max Act: 2.9844. Min Act: -0.1700

Data Index: 710913 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 3.2680. Min Range: -3.2680

Max Act: 2.9685. Min Act: -0.1700

Data Index: 702548 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 3.2680. Min Range: -3.2680

Max Act: 2.9369. Min Act: -0.1700

Data Index: 336443 (C4 (Web Text))

Max Activating Token Index: 226