Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 879 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.5761. Min Act: -0.1700

Data Index: 962602 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.5604. Min Act: -0.1700

Data Index: 1220988 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.5604. Min Act: -0.1700

Data Index: 469255 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.5604. Min Act: -0.1700

Data Index: 1326290 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.5291. Min Act: -0.1700

Data Index: 59915 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.4977. Min Act: -0.1700

Data Index: 560093 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.5447. Min Act: -0.1700

Data Index: 663139 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.5134. Min Act: -0.1700

Data Index: 782399 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.5291. Min Act: -0.1700

Data Index: 528549 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.5134. Min Act: -0.1700

Data Index: 808428 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.4664. Min Act: -0.1700

Data Index: 684607 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.5134. Min Act: -0.1700

Data Index: 424624 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.4664. Min Act: -0.1700

Data Index: 1017439 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.4977. Min Act: -0.1700

Data Index: 1207668 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.4821. Min Act: -0.1700

Data Index: 408702 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.4821. Min Act: -0.1700

Data Index: 743477 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.4664. Min Act: -0.1700

Data Index: 810983 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.4821. Min Act: -0.1700

Data Index: 771904 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.4821. Min Act: -0.1700

Data Index: 923220 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 3.5761. Min Range: -3.5761

Max Act: 3.4821. Min Act: -0.1700

Data Index: 1272042 (C4 (Web Text))

Max Activating Token Index: 644