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

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

Neuron 1916 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: 4.0480. Min Range: -4.0480

Max Act: 4.0480. Min Act: -0.1700

Data Index: 1538530 (Python Code)

Max Activating Token Index: 865

Text #1

Max Range: 4.0480. Min Range: -4.0480

Max Act: 4.0115. Min Act: -0.1700

Data Index: 608625 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9696. Min Act: -0.1700

Data Index: 1505740 (Python Code)

Max Activating Token Index: 999

Text #3

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9296. Min Act: -0.1700

Data Index: 1593716 (Python Code)

Max Activating Token Index: 265

Text #4

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9369. Min Act: -0.1700

Data Index: 473185 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.9170. Min Act: -0.1700

Data Index: 1264239 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.8666. Min Act: -0.1700

Data Index: 1640944 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.8256. Min Act: -0.1700

Data Index: 1354520 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.8477. Min Act: -0.1700

Data Index: 120746 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.8603. Min Act: -0.1700

Data Index: 1629172 (Python Code)

Max Activating Token Index: 762

Text #10

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.7742. Min Act: -0.1700

Data Index: 596310 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.8196. Min Act: -0.1700

Data Index: 521490 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.8347. Min Act: -0.1700

Data Index: 1634845 (Python Code)

Max Activating Token Index: 381

Text #13

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.7918. Min Act: -0.1700

Data Index: 1098385 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.8053. Min Act: -0.1700

Data Index: 960682 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.7386. Min Act: -0.1700

Data Index: 47615 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.7559. Min Act: -0.1700

Data Index: 1388433 (Python Code)

Max Activating Token Index: 386

Text #17

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.7883. Min Act: -0.1700

Data Index: 405326 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.7806. Min Act: -0.1700

Data Index: 99451 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 4.0480. Min Range: -4.0480

Max Act: 3.7441. Min Act: -0.1700

Data Index: 1239812 (C4 (Web Text))

Max Activating Token Index: 215