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

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

Neuron 1715 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: 3.8235. Min Range: -3.8235

Max Act: 3.8235. Min Act: -0.1700

Data Index: 1151192 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7922. Min Act: -0.1700

Data Index: 1009337 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.8235. Min Act: -0.1700

Data Index: 830424 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7922. Min Act: -0.1700

Data Index: 565047 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7922. Min Act: -0.1700

Data Index: 159956 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7609. Min Act: -0.1700

Data Index: 4602 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7609. Min Act: -0.1700

Data Index: 881496 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7296. Min Act: -0.1700

Data Index: 756406 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7296. Min Act: -0.1700

Data Index: 987475 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7296. Min Act: -0.1700

Data Index: 682448 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7296. Min Act: -0.1700

Data Index: 327328 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7296. Min Act: -0.1700

Data Index: 623913 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.7296. Min Act: -0.1700

Data Index: 1041953 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.6984. Min Act: -0.1700

Data Index: 3360 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.6984. Min Act: -0.1700

Data Index: 650197 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.6984. Min Act: -0.1700

Data Index: 911103 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.6671. Min Act: -0.1700

Data Index: 977937 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.6984. Min Act: -0.1700

Data Index: 586176 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.6671. Min Act: -0.1700

Data Index: 954516 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.6671. Min Act: -0.1700

Data Index: 664311 (C4 (Web Text))

Max Activating Token Index: 81