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

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

Neuron 286 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: 3.1506. Min Range: -3.1506

Max Act: 3.1506. Min Act: -0.1700

Data Index: 179282 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 3.1506. Min Range: -3.1506

Max Act: 3.1017. Min Act: -0.1700

Data Index: 575773 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 3.1506. Min Range: -3.1506

Max Act: 3.0527. Min Act: -0.1700

Data Index: 1591130 (Python Code)

Max Activating Token Index: 30

Text #3

Max Range: 3.1506. Min Range: -3.1506

Max Act: 3.0408. Min Act: -0.1700

Data Index: 1247247 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 3.1506. Min Range: -3.1506

Max Act: 3.0417. Min Act: -0.1700

Data Index: 581443 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 3.1506. Min Range: -3.1506

Max Act: 3.0555. Min Act: -0.1700

Data Index: 456223 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 3.1506. Min Range: -3.1506

Max Act: 3.0321. Min Act: -0.1700

Data Index: 894431 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 3.1506. Min Range: -3.1506

Max Act: 2.9834. Min Act: -0.1700

Data Index: 1189434 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 3.1506. Min Range: -3.1506

Max Act: 3.0042. Min Act: -0.1700

Data Index: 344874 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 3.1506. Min Range: -3.1506

Max Act: 2.9900. Min Act: -0.1700

Data Index: 1257108 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 3.1506. Min Range: -3.1506

Max Act: 2.9887. Min Act: -0.1700

Data Index: 497866 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 3.1506. Min Range: -3.1506

Max Act: 2.9714. Min Act: -0.1700

Data Index: 858340 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 3.1506. Min Range: -3.1506

Max Act: 2.9791. Min Act: -0.1700

Data Index: 114419 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 3.1506. Min Range: -3.1506

Max Act: 2.9741. Min Act: -0.1700

Data Index: 794606 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 3.1506. Min Range: -3.1506

Max Act: 2.9631. Min Act: -0.1699

Data Index: 1398023 (Python Code)

Max Activating Token Index: 965

Text #15

Max Range: 3.1506. Min Range: -3.1506

Max Act: 2.9439. Min Act: -0.1700

Data Index: 1616011 (Python Code)

Max Activating Token Index: 525

Text #16

Max Range: 3.1506. Min Range: -3.1506

Max Act: 2.9363. Min Act: -0.1700

Data Index: 1568980 (Python Code)

Max Activating Token Index: 199

Text #17

Max Range: 3.1506. Min Range: -3.1506

Max Act: 2.9422. Min Act: -0.1700

Data Index: 876006 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 3.1506. Min Range: -3.1506

Max Act: 2.9337. Min Act: -0.1700

Data Index: 1146309 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 3.1506. Min Range: -3.1506

Max Act: 2.9350. Min Act: -0.1700

Data Index: 846472 (C4 (Web Text))

Max Activating Token Index: 595