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

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

Neuron 165 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: 4.5649. Min Range: -4.5649

Max Act: 4.5649. Min Act: -0.1700

Data Index: 30478 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.5594. Min Act: -0.1700

Data Index: 1144727 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.5141. Min Act: -0.1700

Data Index: 118791 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.4941. Min Act: -0.1700

Data Index: 415501 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.4478. Min Act: -0.1700

Data Index: 288354 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.3930. Min Act: -0.1700

Data Index: 184635 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.4030. Min Act: -0.1700

Data Index: 1154725 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.4008. Min Act: -0.1700

Data Index: 151504 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.3719. Min Act: -0.1700

Data Index: 1244290 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.3664. Min Act: -0.1700

Data Index: 602142 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.3812. Min Act: -0.1700

Data Index: 586837 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.3823. Min Act: -0.1700

Data Index: 1123157 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.4024. Min Act: -0.1700

Data Index: 1318457 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.3401. Min Act: -0.1700

Data Index: 1161201 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.3416. Min Act: -0.1700

Data Index: 1025527 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.3222. Min Act: -0.1700

Data Index: 1153997 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.3434. Min Act: -0.1700

Data Index: 418844 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.3018. Min Act: -0.1700

Data Index: 245922 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.3208. Min Act: -0.1700

Data Index: 1058829 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.3171. Min Act: -0.1700

Data Index: 897162 (C4 (Web Text))

Max Activating Token Index: 229