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

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

Neuron 1703 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: 5.7152. Min Range: -5.7152

Max Act: 5.7152. Min Act: -0.1700

Data Index: 40592 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.4339. Min Act: -0.1700

Data Index: 77797 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.4339. Min Act: -0.1700

Data Index: 1203128 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.4027. Min Act: -0.1700

Data Index: 1108824 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.3089. Min Act: -0.1700

Data Index: 1144602 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.2777. Min Act: -0.1700

Data Index: 1336596 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.3402. Min Act: -0.1700

Data Index: 153448 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.2777. Min Act: -0.1700

Data Index: 452821 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.2464. Min Act: -0.1700

Data Index: 733999 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.2777. Min Act: -0.1700

Data Index: 95260 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.3089. Min Act: -0.1700

Data Index: 1334796 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.1214. Min Act: -0.1700

Data Index: 12602 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.3402. Min Act: -0.1700

Data Index: 1305583 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.1839. Min Act: -0.1700

Data Index: 28646 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.1839. Min Act: -0.1700

Data Index: 982763 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.1527. Min Act: -0.1700

Data Index: 60216 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.2464. Min Act: -0.1700

Data Index: 517975 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.2152. Min Act: -0.1700

Data Index: 228805 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.1527. Min Act: -0.1700

Data Index: 1270914 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 5.7152. Min Range: -5.7152

Max Act: 5.1527. Min Act: -0.1700

Data Index: 711682 (C4 (Web Text))

Max Activating Token Index: 899