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

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

Neuron 279 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: 3.1911. Min Range: -3.1911

Max Act: 3.1911. Min Act: -0.1700

Data Index: 1151806 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 3.1911. Min Range: -3.1911

Max Act: 3.1377. Min Act: -0.1700

Data Index: 862446 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 3.1911. Min Range: -3.1911

Max Act: 3.0610. Min Act: -0.1700

Data Index: 942605 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 3.1911. Min Range: -3.1911

Max Act: 3.0724. Min Act: -0.1700

Data Index: 940631 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 3.1911. Min Range: -3.1911

Max Act: 3.0552. Min Act: -0.1700

Data Index: 1199085 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 3.1911. Min Range: -3.1911

Max Act: 3.0382. Min Act: -0.1700

Data Index: 818702 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 3.1911. Min Range: -3.1911

Max Act: 3.0131. Min Act: -0.1700

Data Index: 200402 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 3.1911. Min Range: -3.1911

Max Act: 3.0133. Min Act: -0.1700

Data Index: 351646 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 3.1911. Min Range: -3.1911

Max Act: 3.0129. Min Act: -0.1700

Data Index: 379959 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 3.1911. Min Range: -3.1911

Max Act: 3.0140. Min Act: -0.1700

Data Index: 68016 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.9905. Min Act: -0.1700

Data Index: 260984 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.9987. Min Act: -0.1700

Data Index: 421723 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.9803. Min Act: -0.1700

Data Index: 252651 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.9358. Min Act: -0.1700

Data Index: 286095 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.9199. Min Act: -0.1700

Data Index: 1253881 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.9310. Min Act: -0.1699

Data Index: 855810 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.8969. Min Act: -0.1700

Data Index: 149348 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.9140. Min Act: -0.1700

Data Index: 674496 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.8937. Min Act: -0.1700

Data Index: 221595 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.8955. Min Act: -0.1700

Data Index: 750434 (C4 (Web Text))

Max Activating Token Index: 227