Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1515 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.9154. Min Act: -0.1700

Data Index: 75393 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.7903. Min Act: -0.1700

Data Index: 655714 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.7590. Min Act: -0.1700

Data Index: 658343 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.7903. Min Act: -0.1700

Data Index: 876534 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.7277. Min Act: -0.1700

Data Index: 366140 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.6964. Min Act: -0.1700

Data Index: 776843 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.6964. Min Act: -0.1700

Data Index: 1275891 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.6964. Min Act: -0.1700

Data Index: 72535 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.7277. Min Act: -0.1700

Data Index: 1012500 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.7277. Min Act: -0.1700

Data Index: 991331 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.6651. Min Act: -0.1700

Data Index: 1014259 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.6964. Min Act: -0.1700

Data Index: 921137 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.6651. Min Act: -0.1700

Data Index: 1097066 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.6338. Min Act: -0.1700

Data Index: 310878 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.6964. Min Act: -0.1700

Data Index: 375349 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.6651. Min Act: -0.1700

Data Index: 255162 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.6025. Min Act: -0.1700

Data Index: 515126 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.6338. Min Act: -0.1700

Data Index: 868040 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.6338. Min Act: -0.1700

Data Index: 1358342 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 3.9154. Min Range: -3.9154

Max Act: 3.6651. Min Act: -0.1700

Data Index: 579727 (C4 (Web Text))

Max Activating Token Index: 532