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

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

Neuron 1235 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: 5.4024. Min Range: -5.4024

Max Act: 5.4024. Min Act: -0.1700

Data Index: 80711 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.2461. Min Act: -0.1700

Data Index: 97953 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.2774. Min Act: -0.1700

Data Index: 1144844 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.2149. Min Act: -0.1700

Data Index: 724102 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.2149. Min Act: -0.1700

Data Index: 116506 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.2461. Min Act: -0.1700

Data Index: 987056 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.2149. Min Act: -0.1700

Data Index: 1650249 (Python Code)

Max Activating Token Index: 966

Text #7

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.1836. Min Act: -0.1700

Data Index: 1057083 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.2149. Min Act: -0.1698

Data Index: 760818 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.2149. Min Act: -0.1700

Data Index: 796110 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.1836. Min Act: -0.1700

Data Index: 594425 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.2149. Min Act: -0.1700

Data Index: 1298913 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.2149. Min Act: -0.1700

Data Index: 1163520 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.2149. Min Act: -0.1700

Data Index: 136172 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.1211. Min Act: -0.1700

Data Index: 1220515 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.1836. Min Act: -0.1700

Data Index: 103302 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.1211. Min Act: -0.1699

Data Index: 186901 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.1524. Min Act: -0.1700

Data Index: 996457 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.1211. Min Act: -0.1700

Data Index: 636125 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 5.4024. Min Range: -5.4024

Max Act: 5.1524. Min Act: -0.1700

Data Index: 328466 (C4 (Web Text))

Max Activating Token Index: 444