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

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

Neuron 1215 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: 3.4162. Min Range: -3.4162

Max Act: 3.4162. Min Act: -0.1700

Data Index: 1250684 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.3086. Min Act: -0.1700

Data Index: 693533 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.2751. Min Act: -0.1700

Data Index: 417160 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.2242. Min Act: -0.1700

Data Index: 312851 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.2636. Min Act: -0.1700

Data Index: 383691 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.2214. Min Act: -0.1700

Data Index: 26891 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.2392. Min Act: -0.1700

Data Index: 479145 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.2332. Min Act: -0.1700

Data Index: 767951 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.1809. Min Act: -0.1700

Data Index: 936648 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.1885. Min Act: -0.1700

Data Index: 930581 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.1885. Min Act: -0.1700

Data Index: 1323885 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.1621. Min Act: -0.1700

Data Index: 131469 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.1777. Min Act: -0.1700

Data Index: 1167193 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.1787. Min Act: -0.1700

Data Index: 915960 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.1378. Min Act: -0.1700

Data Index: 239399 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.1521. Min Act: -0.1700

Data Index: 95333 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.1522. Min Act: -0.1700

Data Index: 765290 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.1355. Min Act: -0.1700

Data Index: 219147 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.1446. Min Act: -0.1700

Data Index: 522792 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 3.4162. Min Range: -3.4162

Max Act: 3.1140. Min Act: -0.1700

Data Index: 1056253 (C4 (Web Text))

Max Activating Token Index: 682