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

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

Neuron 1645 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: 3.9564. Min Range: -3.9564

Max Act: 3.9564. Min Act: -0.1699

Data Index: 418270 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.9314. Min Act: -0.1700

Data Index: 498652 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.7713. Min Act: -0.1700

Data Index: 1422089 (Python Code)

Max Activating Token Index: 254

Text #3

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.6579. Min Act: -0.1699

Data Index: 875656 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.6328. Min Act: -0.1700

Data Index: 839171 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.5825. Min Act: -0.1700

Data Index: 32135 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.5953. Min Act: -0.1699

Data Index: 858270 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.5622. Min Act: -0.1700

Data Index: 1580279 (Python Code)

Max Activating Token Index: 1004

Text #8

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.5209. Min Act: -0.1700

Data Index: 1160829 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.5520. Min Act: -0.1700

Data Index: 1189452 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.5562. Min Act: -0.1700

Data Index: 545710 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.5431. Min Act: -0.1699

Data Index: 88960 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.5090. Min Act: -0.1699

Data Index: 262127 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.5377. Min Act: -0.1700

Data Index: 693178 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.5151. Min Act: -0.1700

Data Index: 987206 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.5156. Min Act: -0.1699

Data Index: 112622 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.5007. Min Act: -0.1697

Data Index: 1042871 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.4846. Min Act: -0.1700

Data Index: 1219109 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.4809. Min Act: -0.1692

Data Index: 886225 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 3.9564. Min Range: -3.9564

Max Act: 3.4620. Min Act: -0.1700

Data Index: 637820 (C4 (Web Text))

Max Activating Token Index: 64