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

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

Neuron 1441 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.8054. Min Act: -0.1700

Data Index: 971530 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.7741. Min Act: -0.1700

Data Index: 509520 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.7741. Min Act: -0.1700

Data Index: 246512 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.6491. Min Act: -0.1700

Data Index: 647020 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.7741. Min Act: -0.1700

Data Index: 421639 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.7429. Min Act: -0.1700

Data Index: 175324 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.7429. Min Act: -0.1700

Data Index: 710859 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.7429. Min Act: -0.1700

Data Index: 955281 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.7741. Min Act: -0.1700

Data Index: 1108870 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.7116. Min Act: -0.1700

Data Index: 715491 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.7429. Min Act: -0.1700

Data Index: 1013159 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.6804. Min Act: -0.1700

Data Index: 703073 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.6804. Min Act: -0.1700

Data Index: 583620 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.7116. Min Act: -0.1700

Data Index: 1350635 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.7116. Min Act: -0.1700

Data Index: 111677 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.6804. Min Act: -0.1700

Data Index: 224720 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.7429. Min Act: -0.1700

Data Index: 855555 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.7429. Min Act: -0.1700

Data Index: 1248238 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.7116. Min Act: -0.1700

Data Index: 699426 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 5.8054. Min Range: -5.8054

Max Act: 5.6804. Min Act: -0.1700

Data Index: 197924 (C4 (Web Text))

Max Activating Token Index: 419