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

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

Neuron 1485 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: 3.2023. Min Range: -3.2023

Max Act: 3.2019. Min Act: -0.1700

Data Index: 209160 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.2023. Min Act: -0.1700

Data Index: 1329681 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1919. Min Act: -0.1700

Data Index: 1394502 (Python Code)

Max Activating Token Index: 504

Text #3

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1802. Min Act: -0.1700

Data Index: 1565394 (Python Code)

Max Activating Token Index: 58

Text #4

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1513. Min Act: -0.1700

Data Index: 1379275 (Python Code)

Max Activating Token Index: 980

Text #5

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1756. Min Act: -0.1700

Data Index: 270331 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1461. Min Act: -0.1700

Data Index: 1103577 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1518. Min Act: -0.1700

Data Index: 1648713 (Python Code)

Max Activating Token Index: 677

Text #8

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1486. Min Act: -0.1700

Data Index: 587002 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1525. Min Act: -0.1700

Data Index: 345173 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1548. Min Act: -0.1700

Data Index: 771854 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1362. Min Act: -0.1700

Data Index: 1069492 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1610. Min Act: -0.1700

Data Index: 716949 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1465. Min Act: -0.1700

Data Index: 1497357 (Python Code)

Max Activating Token Index: 69

Text #14

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1319. Min Act: -0.1700

Data Index: 1553853 (Python Code)

Max Activating Token Index: 112

Text #15

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1048. Min Act: -0.1700

Data Index: 1367606 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.0838. Min Act: -0.1700

Data Index: 1127412 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.0985. Min Act: -0.1700

Data Index: 1542575 (Python Code)

Max Activating Token Index: 535

Text #18

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.0933. Min Act: -0.1700

Data Index: 1456667 (Python Code)

Max Activating Token Index: 84

Text #19

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.0766. Min Act: -0.1700

Data Index: 1376664 (Python Code)

Max Activating Token Index: 457