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

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

Neuron 84 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: 3.3548. Min Range: -3.3548

Max Act: 3.3548. Min Act: -0.1700

Data Index: 927253 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.3305. Min Act: -0.1700

Data Index: 714918 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.2306. Min Act: -0.1700

Data Index: 349801 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.2229. Min Act: -0.1700

Data Index: 17484 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.2071. Min Act: -0.1700

Data Index: 1023140 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.1991. Min Act: -0.1700

Data Index: 345995 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.1898. Min Act: -0.1700

Data Index: 1310464 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.1918. Min Act: -0.1695

Data Index: 1014430 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.1557. Min Act: -0.1700

Data Index: 991661 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.1456. Min Act: -0.1700

Data Index: 152083 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.1539. Min Act: -0.1700

Data Index: 681317 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.1581. Min Act: -0.1700

Data Index: 811714 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.1345. Min Act: -0.1699

Data Index: 1017577 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.1311. Min Act: -0.1700

Data Index: 115970 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.1248. Min Act: -0.1700

Data Index: 952905 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.1171. Min Act: -0.1700

Data Index: 675596 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.0991. Min Act: -0.1694

Data Index: 503701 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.1089. Min Act: -0.1700

Data Index: 80659 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.1169. Min Act: -0.1700

Data Index: 483408 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 3.3548. Min Range: -3.3548

Max Act: 3.1006. Min Act: -0.1700

Data Index: 434780 (C4 (Web Text))

Max Activating Token Index: 292