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

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

Neuron 778 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: 4.3793. Min Range: -4.3793

Max Act: 4.3793. Min Act: -0.1698

Data Index: 1310883 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.3525. Min Act: -0.1700

Data Index: 1580945 (Python Code)

Max Activating Token Index: 414

Text #2

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.3389. Min Act: -0.1699

Data Index: 1458254 (Python Code)

Max Activating Token Index: 527

Text #3

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.2671. Min Act: -0.1699

Data Index: 1450570 (Python Code)

Max Activating Token Index: 290

Text #4

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.2415. Min Act: -0.1700

Data Index: 381608 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.2121. Min Act: -0.1699

Data Index: 1468009 (Python Code)

Max Activating Token Index: 332

Text #6

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.2016. Min Act: -0.1699

Data Index: 1431984 (Python Code)

Max Activating Token Index: 446

Text #7

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.2098. Min Act: -0.1699

Data Index: 1476937 (Python Code)

Max Activating Token Index: 844

Text #8

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.1644. Min Act: -0.1700

Data Index: 1623279 (Python Code)

Max Activating Token Index: 685

Text #9

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.1675. Min Act: -0.1698

Data Index: 1527231 (Python Code)

Max Activating Token Index: 725

Text #10

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.1374. Min Act: -0.1700

Data Index: 776668 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.1679. Min Act: -0.1699

Data Index: 909768 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.1565. Min Act: -0.1699

Data Index: 994745 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.1335. Min Act: -0.1698

Data Index: 1068664 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.1113. Min Act: -0.1700

Data Index: 1395998 (Python Code)

Max Activating Token Index: 799

Text #15

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.1109. Min Act: -0.1700

Data Index: 1429365 (Python Code)

Max Activating Token Index: 239

Text #16

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.1085. Min Act: -0.1700

Data Index: 1052474 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.1271. Min Act: -0.1698

Data Index: 340555 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.0738. Min Act: -0.1700

Data Index: 1418078 (Python Code)

Max Activating Token Index: 759

Text #19

Max Range: 4.3793. Min Range: -4.3793

Max Act: 4.0938. Min Act: -0.1700

Data Index: 1549848 (Python Code)

Max Activating Token Index: 405