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

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

Neuron 1647 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: 2.9449. Min Range: -2.9449

Max Act: 2.9397. Min Act: -0.1699

Data Index: 1221087 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.9449. Min Act: -0.1532

Data Index: 288893 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.9271. Min Act: -0.1700

Data Index: 218253 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.9106. Min Act: -0.1699

Data Index: 486559 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8787. Min Act: -0.1698

Data Index: 537130 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8946. Min Act: -0.1700

Data Index: 1049123 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8606. Min Act: -0.1700

Data Index: 531307 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8609. Min Act: -0.1700

Data Index: 1179234 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8736. Min Act: -0.1700

Data Index: 987986 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8501. Min Act: -0.1696

Data Index: 1574623 (Python Code)

Max Activating Token Index: 250

Text #10

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8526. Min Act: -0.1700

Data Index: 937432 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8491. Min Act: -0.1700

Data Index: 1191252 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8598. Min Act: -0.1699

Data Index: 936215 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8442. Min Act: -0.1700

Data Index: 1175313 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8308. Min Act: -0.1700

Data Index: 983795 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8336. Min Act: -0.1700

Data Index: 1270150 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8321. Min Act: -0.1699

Data Index: 1186600 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8296. Min Act: -0.1697

Data Index: 1381960 (Python Code)

Max Activating Token Index: 1008

Text #18

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8193. Min Act: -0.1700

Data Index: 348551 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 2.9449. Min Range: -2.9449

Max Act: 2.8154. Min Act: -0.1700

Data Index: 815680 (C4 (Web Text))

Max Activating Token Index: 494