Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 425 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.4868. Min Act: -0.1700

Data Index: 27720 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.4243. Min Act: -0.1700

Data Index: 311109 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.3618. Min Act: -0.1700

Data Index: 975420 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.3618. Min Act: -0.1700

Data Index: 773675 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.3618. Min Act: -0.1700

Data Index: 113792 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.3306. Min Act: -0.1700

Data Index: 225152 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.3931. Min Act: -0.1700

Data Index: 935608 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.2993. Min Act: -0.1700

Data Index: 526084 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.2681. Min Act: -0.1700

Data Index: 190842 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.2681. Min Act: -0.1700

Data Index: 99223 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.2993. Min Act: -0.1700

Data Index: 397371 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.3931. Min Act: -0.1700

Data Index: 1334994 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.2681. Min Act: -0.1700

Data Index: 557107 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.2681. Min Act: -0.1700

Data Index: 754917 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.0181. Min Act: -0.1700

Data Index: 227374 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.1431. Min Act: -0.1700

Data Index: 886681 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.1431. Min Act: -0.1700

Data Index: 823332 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.1118. Min Act: -0.1700

Data Index: 153788 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 5.4868. Min Range: -5.4868

Max Act: 4.9868. Min Act: -0.1700

Data Index: 1039678 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 5.4868. Min Range: -5.4868

Max Act: 5.1118. Min Act: -0.1700

Data Index: 993258 (C4 (Web Text))

Max Activating Token Index: 1018