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

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

Neuron 989 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: 3.4473. Min Range: -3.4473

Max Act: 3.4473. Min Act: -0.1700

Data Index: 766895 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.3515. Min Act: -0.1699

Data Index: 756532 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.3616. Min Act: -0.1699

Data Index: 655049 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.3473. Min Act: -0.1700

Data Index: 1138918 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.3452. Min Act: -0.1700

Data Index: 1030181 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.3135. Min Act: -0.1700

Data Index: 515160 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.3023. Min Act: -0.1671

Data Index: 23554 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.3012. Min Act: -0.1699

Data Index: 358514 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.2749. Min Act: -0.1700

Data Index: 668151 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.2812. Min Act: -0.1693

Data Index: 775962 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.2756. Min Act: -0.1700

Data Index: 1217210 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.2658. Min Act: -0.1700

Data Index: 286979 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.2607. Min Act: -0.1699

Data Index: 602242 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.2367. Min Act: -0.1700

Data Index: 1066538 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.2542. Min Act: -0.1700

Data Index: 1074533 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.2531. Min Act: -0.1700

Data Index: 981717 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.2328. Min Act: -0.1700

Data Index: 1106769 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.2305. Min Act: -0.1700

Data Index: 674600 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.2324. Min Act: -0.1700

Data Index: 617761 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 3.4473. Min Range: -3.4473

Max Act: 3.2403. Min Act: -0.1700

Data Index: 1072125 (C4 (Web Text))

Max Activating Token Index: 932