Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1166 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.4068. Min Act: -0.1700

Data Index: 261096 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3187. Min Act: -0.1700

Data Index: 831919 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.3068. Min Act: -0.1700

Data Index: 1026660 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2599. Min Act: -0.1700

Data Index: 509682 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2556. Min Act: -0.1700

Data Index: 228882 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2606. Min Act: -0.1700

Data Index: 328976 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2073. Min Act: -0.1700

Data Index: 1214059 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2188. Min Act: -0.1700

Data Index: 462647 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1879. Min Act: -0.1700

Data Index: 416247 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2040. Min Act: -0.1692

Data Index: 1069873 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1714. Min Act: -0.1700

Data Index: 448147 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1785. Min Act: -0.1700

Data Index: 378741 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1698. Min Act: -0.1700

Data Index: 39674 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1637. Min Act: -0.1700

Data Index: 55404 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1416. Min Act: -0.1700

Data Index: 1265055 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1392. Min Act: -0.1700

Data Index: 253186 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1318. Min Act: -0.1700

Data Index: 21594 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1453. Min Act: -0.1699

Data Index: 71018 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1230. Min Act: -0.1700

Data Index: 1022369 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1261. Min Act: -0.1700

Data Index: 896037 (C4 (Web Text))

Max Activating Token Index: 880