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

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

Neuron 375 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1211. Min Range: -6.1211

Max Act: 6.1211. Min Act: -0.1700

Data Index: 310944 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.8086. Min Act: -0.1700

Data Index: 101993 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.6836. Min Act: -0.1700

Data Index: 84098 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.6523. Min Act: -0.1700

Data Index: 293173 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.6523. Min Act: -0.1700

Data Index: 707165 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.6211. Min Act: -0.1700

Data Index: 343260 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.5273. Min Act: -0.1700

Data Index: 95707 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.5586. Min Act: -0.1700

Data Index: 80657 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.5586. Min Act: -0.1700

Data Index: 1165902 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.4961. Min Act: -0.1700

Data Index: 678301 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.5586. Min Act: -0.1700

Data Index: 297858 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.4961. Min Act: -0.1700

Data Index: 862526 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.4961. Min Act: -0.1700

Data Index: 365049 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.4961. Min Act: -0.1700

Data Index: 241432 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.4961. Min Act: -0.1700

Data Index: 132978 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.4648. Min Act: -0.1700

Data Index: 934040 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.4648. Min Act: -0.1700

Data Index: 508397 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.4648. Min Act: -0.1700

Data Index: 282416 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.4648. Min Act: -0.1700

Data Index: 838892 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 6.1211. Min Range: -6.1211

Max Act: 5.4336. Min Act: -0.1700

Data Index: 82837 (C4 (Web Text))

Max Activating Token Index: 1023