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

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

Neuron 361 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: 3.1638. Min Range: -3.1638

Max Act: 3.1590. Min Act: -0.1700

Data Index: 1124722 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 3.1638. Min Range: -3.1638

Max Act: 3.1355. Min Act: -0.1700

Data Index: 1390376 (Python Code)

Max Activating Token Index: 339

Text #2

Max Range: 3.1638. Min Range: -3.1638

Max Act: 3.1638. Min Act: -0.1700

Data Index: 1057084 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 3.1638. Min Range: -3.1638

Max Act: 3.0859. Min Act: -0.1700

Data Index: 1623420 (Python Code)

Max Activating Token Index: 555

Text #4

Max Range: 3.1638. Min Range: -3.1638

Max Act: 3.0734. Min Act: -0.1700

Data Index: 1385341 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 3.1638. Min Range: -3.1638

Max Act: 3.0156. Min Act: -0.1700

Data Index: 802034 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 3.1638. Min Range: -3.1638

Max Act: 3.0319. Min Act: -0.1700

Data Index: 578635 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 3.1638. Min Range: -3.1638

Max Act: 3.0215. Min Act: -0.1700

Data Index: 1556339 (Python Code)

Max Activating Token Index: 462

Text #8

Max Range: 3.1638. Min Range: -3.1638

Max Act: 2.9973. Min Act: -0.1700

Data Index: 134619 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 3.1638. Min Range: -3.1638

Max Act: 2.9770. Min Act: -0.1700

Data Index: 1285959 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 3.1638. Min Range: -3.1638

Max Act: 3.0213. Min Act: -0.1700

Data Index: 1023564 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 3.1638. Min Range: -3.1638

Max Act: 2.9760. Min Act: -0.1700

Data Index: 1107988 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 3.1638. Min Range: -3.1638

Max Act: 2.9558. Min Act: -0.1700

Data Index: 973114 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 3.1638. Min Range: -3.1638

Max Act: 2.9136. Min Act: -0.1700

Data Index: 404856 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 3.1638. Min Range: -3.1638

Max Act: 2.9038. Min Act: -0.1700

Data Index: 208498 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 3.1638. Min Range: -3.1638

Max Act: 3.0103. Min Act: -0.1700

Data Index: 1427066 (Python Code)

Max Activating Token Index: 965

Text #16

Max Range: 3.1638. Min Range: -3.1638

Max Act: 2.9059. Min Act: -0.1700

Data Index: 64992 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 3.1638. Min Range: -3.1638

Max Act: 2.9145. Min Act: -0.1700

Data Index: 801550 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 3.1638. Min Range: -3.1638

Max Act: 2.9259. Min Act: -0.1700

Data Index: 318915 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 3.1638. Min Range: -3.1638

Max Act: 2.9559. Min Act: -0.1700

Data Index: 1275392 (C4 (Web Text))

Max Activating Token Index: 1012