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

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

Neuron 1426 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: 3.8254. Min Range: -3.8254

Max Act: 3.8254. Min Act: -0.1700

Data Index: 300032 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.7644. Min Act: -0.1700

Data Index: 820773 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.7687. Min Act: -0.1700

Data Index: 1236493 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6332. Min Act: -0.1700

Data Index: 872444 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5935. Min Act: -0.1700

Data Index: 222934 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5686. Min Act: -0.1700

Data Index: 112752 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5779. Min Act: -0.1700

Data Index: 740844 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5439. Min Act: -0.1700

Data Index: 1250103 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5285. Min Act: -0.1700

Data Index: 1244807 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5229. Min Act: -0.1700

Data Index: 118047 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5064. Min Act: -0.1700

Data Index: 522761 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.4997. Min Act: -0.1700

Data Index: 468480 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5116. Min Act: -0.1700

Data Index: 1235626 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.4754. Min Act: -0.1700

Data Index: 1179380 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.4680. Min Act: -0.1700

Data Index: 146843 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.4510. Min Act: -0.1700

Data Index: 1325381 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.4572. Min Act: -0.1700

Data Index: 345464 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.4565. Min Act: -0.1700

Data Index: 456684 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.4419. Min Act: -0.1700

Data Index: 940698 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.4542. Min Act: -0.1700

Data Index: 1247316 (C4 (Web Text))

Max Activating Token Index: 336