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

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

Neuron 430 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: 9.1673. Min Range: -9.1673

Max Act: 9.1673. Min Act: -0.1700

Data Index: 523960 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.8917. Min Act: -0.1700

Data Index: 792670 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.8513. Min Act: -0.1700

Data Index: 368530 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.8540. Min Act: -0.1700

Data Index: 505257 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.5909. Min Act: -0.1700

Data Index: 524346 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.5328. Min Act: -0.1700

Data Index: 547910 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.4968. Min Act: -0.1700

Data Index: 1314796 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.4215. Min Act: -0.1700

Data Index: 286013 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.4200. Min Act: -0.1700

Data Index: 202083 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.2995. Min Act: -0.1700

Data Index: 1116974 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.2274. Min Act: -0.1700

Data Index: 55763 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.3194. Min Act: -0.1700

Data Index: 938941 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.2803. Min Act: -0.1700

Data Index: 874818 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.2719. Min Act: -0.1700

Data Index: 605013 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.2947. Min Act: -0.1700

Data Index: 464230 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.2198. Min Act: -0.1700

Data Index: 416683 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.2605. Min Act: -0.1700

Data Index: 246635 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.2530. Min Act: -0.1700

Data Index: 813222 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.2403. Min Act: -0.1700

Data Index: 1150644 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 9.1673. Min Range: -9.1673

Max Act: 8.2712. Min Act: -0.1700

Data Index: 1150151 (C4 (Web Text))

Max Activating Token Index: 216