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

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

Neuron 978 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: 3.9931. Min Range: -3.9931

Max Act: 3.9931. Min Act: -0.1700

Data Index: 1210023 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.8055. Min Act: -0.1700

Data Index: 1160318 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.7742. Min Act: -0.1700

Data Index: 756324 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.7429. Min Act: -0.1700

Data Index: 712893 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.6803. Min Act: -0.1700

Data Index: 703059 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.7116. Min Act: -0.1700

Data Index: 1254427 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.6803. Min Act: -0.1700

Data Index: 127741 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.6177. Min Act: -0.1700

Data Index: 1350412 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.6490. Min Act: -0.1700

Data Index: 939335 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.6803. Min Act: -0.1700

Data Index: 470676 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.6177. Min Act: -0.1700

Data Index: 540732 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.6177. Min Act: -0.1700

Data Index: 375723 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.6177. Min Act: -0.1700

Data Index: 1321193 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.5864. Min Act: -0.1700

Data Index: 85867 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.5864. Min Act: -0.1700

Data Index: 1269979 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.5864. Min Act: -0.1700

Data Index: 237011 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.5864. Min Act: -0.1700

Data Index: 901891 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.5864. Min Act: -0.1700

Data Index: 1179263 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.5864. Min Act: -0.1700

Data Index: 552129 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 3.9931. Min Range: -3.9931

Max Act: 3.5551. Min Act: -0.1700

Data Index: 332454 (C4 (Web Text))

Max Activating Token Index: 184