Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1333 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1138. Min Range: -3.1138

Max Act: 3.1138. Min Act: -0.1700

Data Index: 1312030 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.8448. Min Act: -0.1700

Data Index: 1228186 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.8289. Min Act: -0.1700

Data Index: 725028 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.8130. Min Act: -0.1700

Data Index: 573814 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7971. Min Act: -0.1700

Data Index: 1031656 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7013. Min Act: -0.1700

Data Index: 1160096 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7493. Min Act: -0.1700

Data Index: 582244 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7333. Min Act: -0.1700

Data Index: 856194 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7173. Min Act: -0.1700

Data Index: 356089 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7173. Min Act: -0.1700

Data Index: 1093081 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7173. Min Act: -0.1700

Data Index: 1210486 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7173. Min Act: -0.1700

Data Index: 937179 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7013. Min Act: -0.1700

Data Index: 1188051 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7013. Min Act: -0.1700

Data Index: 278396 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7173. Min Act: -0.1700

Data Index: 18667 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7013. Min Act: -0.1700

Data Index: 770702 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7013. Min Act: -0.1700

Data Index: 938759 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6853. Min Act: -0.1700

Data Index: 508822 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6853. Min Act: -0.1700

Data Index: 324927 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6853. Min Act: -0.1700

Data Index: 1276725 (C4 (Web Text))

Max Activating Token Index: 261