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

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

Neuron 1084 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: 3.3662. Min Range: -3.3662

Max Act: 3.3662. Min Act: -0.1700

Data Index: 300064 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.2457. Min Act: -0.1700

Data Index: 393189 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.2356. Min Act: -0.1700

Data Index: 1476032 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.2428. Min Act: -0.1700

Data Index: 1090299 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.2002. Min Act: -0.1700

Data Index: 1610722 (Python Code)

Max Activating Token Index: 412

Text #5

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.1928. Min Act: -0.1700

Data Index: 644764 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.1601. Min Act: -0.1700

Data Index: 1281543 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.1484. Min Act: -0.1700

Data Index: 394239 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.1515. Min Act: -0.1700

Data Index: 709586 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.1439. Min Act: -0.1700

Data Index: 1494723 (Python Code)

Max Activating Token Index: 54

Text #10

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.1440. Min Act: -0.1700

Data Index: 1621480 (Python Code)

Max Activating Token Index: 371

Text #11

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.1554. Min Act: -0.1700

Data Index: 603277 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.1363. Min Act: -0.1700

Data Index: 1051932 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.1344. Min Act: -0.1700

Data Index: 609674 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.1162. Min Act: -0.1700

Data Index: 434614 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.1036. Min Act: -0.1700

Data Index: 378664 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.1068. Min Act: -0.1700

Data Index: 881447 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.1038. Min Act: -0.1700

Data Index: 277909 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.1126. Min Act: -0.1700

Data Index: 884276 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 3.3662. Min Range: -3.3662

Max Act: 3.0922. Min Act: -0.1700

Data Index: 759564 (C4 (Web Text))

Max Activating Token Index: 1013