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

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

Neuron 1438 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: 4.1057. Min Range: -4.1057

Max Act: 4.1057. Min Act: -0.1700

Data Index: 1243583 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 4.1057. Min Range: -4.1057

Max Act: 4.0734. Min Act: -0.1700

Data Index: 1291907 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.9538. Min Act: -0.1700

Data Index: 866735 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.9595. Min Act: -0.1700

Data Index: 88942 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.9323. Min Act: -0.1700

Data Index: 639165 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.8857. Min Act: -0.1700

Data Index: 510804 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.8717. Min Act: -0.1700

Data Index: 177197 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.8752. Min Act: -0.1700

Data Index: 660185 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.8721. Min Act: -0.1700

Data Index: 430078 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.8735. Min Act: -0.1700

Data Index: 383378 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.8336. Min Act: -0.1700

Data Index: 371725 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.8309. Min Act: -0.1700

Data Index: 1198267 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.8207. Min Act: -0.1700

Data Index: 452650 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.8169. Min Act: -0.1700

Data Index: 815085 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.8359. Min Act: -0.1700

Data Index: 171834 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.8262. Min Act: -0.1700

Data Index: 118214 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.8249. Min Act: -0.1700

Data Index: 406208 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.8143. Min Act: -0.1700

Data Index: 621171 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.8161. Min Act: -0.1700

Data Index: 1116484 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 4.1057. Min Range: -4.1057

Max Act: 3.7945. Min Act: -0.1700

Data Index: 226810 (C4 (Web Text))

Max Activating Token Index: 822