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

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

Neuron 786 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1017. Min Range: -5.1017

Max Act: 5.1017. Min Act: -0.1700

Data Index: 148043 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 5.1017. Min Range: -5.1017

Max Act: 5.0392. Min Act: -0.1700

Data Index: 1020442 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 5.1017. Min Range: -5.1017

Max Act: 5.0080. Min Act: -0.1700

Data Index: 859522 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.9767. Min Act: -0.1700

Data Index: 274220 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.9767. Min Act: -0.1700

Data Index: 617925 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.9142. Min Act: -0.1700

Data Index: 277 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.9142. Min Act: -0.1700

Data Index: 464537 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.9455. Min Act: -0.1700

Data Index: 220458 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.9142. Min Act: -0.1700

Data Index: 1091116 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.9142. Min Act: -0.1700

Data Index: 1305584 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.9142. Min Act: -0.1700

Data Index: 852089 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.8830. Min Act: -0.1700

Data Index: 956894 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.8830. Min Act: -0.1700

Data Index: 356628 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.8517. Min Act: -0.1700

Data Index: 1018013 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.8830. Min Act: -0.1700

Data Index: 640248 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.8517. Min Act: -0.1700

Data Index: 811608 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.8205. Min Act: -0.1700

Data Index: 227536 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.8830. Min Act: -0.1700

Data Index: 1290064 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.8517. Min Act: -0.1700

Data Index: 148151 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 5.1017. Min Range: -5.1017

Max Act: 4.8205. Min Act: -0.1700

Data Index: 374289 (C4 (Web Text))

Max Activating Token Index: 279