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

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

Neuron 1294 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: 3.3333. Min Range: -3.3333

Max Act: 3.3333. Min Act: -0.1700

Data Index: 1630102 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.3086. Min Act: -0.1700

Data Index: 428192 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.1693. Min Act: -0.1700

Data Index: 1500764 (Python Code)

Max Activating Token Index: 113

Text #3

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.1727. Min Act: -0.1700

Data Index: 1391867 (Python Code)

Max Activating Token Index: 215

Text #4

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.1533. Min Act: -0.1700

Data Index: 378979 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.1526. Min Act: -0.1700

Data Index: 546540 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.1596. Min Act: -0.1700

Data Index: 380590 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.1250. Min Act: -0.1700

Data Index: 558956 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.0946. Min Act: -0.1700

Data Index: 717715 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.0781. Min Act: -0.1700

Data Index: 108152 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.0783. Min Act: -0.1700

Data Index: 662582 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.0326. Min Act: -0.1700

Data Index: 1050648 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.0267. Min Act: -0.1700

Data Index: 1132175 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.0244. Min Act: -0.1700

Data Index: 888934 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.0229. Min Act: -0.1700

Data Index: 1349043 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.0240. Min Act: -0.1700

Data Index: 1278662 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.0127. Min Act: -0.1700

Data Index: 805011 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.0114. Min Act: -0.1700

Data Index: 1112213 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.0211. Min Act: -0.1700

Data Index: 94798 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 3.3333. Min Range: -3.3333

Max Act: 3.0209. Min Act: -0.1700

Data Index: 145019 (C4 (Web Text))

Max Activating Token Index: 473