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

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

Neuron 196 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1567. Min Range: -5.1567

Max Act: 5.1567. Min Act: -0.1700

Data Index: 645344 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 5.1567. Min Range: -5.1567

Max Act: 5.0005. Min Act: -0.1700

Data Index: 1244555 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.9692. Min Act: -0.1700

Data Index: 1178664 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.9380. Min Act: -0.1700

Data Index: 690548 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.8442. Min Act: -0.1700

Data Index: 1220313 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.6880. Min Act: -0.1700

Data Index: 1003563 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.8130. Min Act: -0.1700

Data Index: 5295 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.8130. Min Act: -0.1700

Data Index: 368121 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.8130. Min Act: -0.1700

Data Index: 1205820 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.8442. Min Act: -0.1700

Data Index: 776789 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.7817. Min Act: -0.1700

Data Index: 794445 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.8130. Min Act: -0.1700

Data Index: 877015 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.8130. Min Act: -0.1700

Data Index: 10367 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.8130. Min Act: -0.1700

Data Index: 236699 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.7817. Min Act: -0.1700

Data Index: 370071 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.8130. Min Act: -0.1700

Data Index: 435672 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.7505. Min Act: -0.1700

Data Index: 514215 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.7192. Min Act: -0.1700

Data Index: 1140207 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.7817. Min Act: -0.1700

Data Index: 947999 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 5.1567. Min Range: -5.1567

Max Act: 4.7192. Min Act: -0.1700

Data Index: 1132731 (C4 (Web Text))

Max Activating Token Index: 957