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

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

Neuron 1252 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: 5.8804. Min Range: -5.8804

Max Act: 5.8804. Min Act: -0.1700

Data Index: 812716 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.6929. Min Act: -0.1700

Data Index: 568894 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.6304. Min Act: -0.1700

Data Index: 1055950 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.5991. Min Act: -0.1700

Data Index: 790382 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.6304. Min Act: -0.1700

Data Index: 850300 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.5679. Min Act: -0.1700

Data Index: 449025 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.5991. Min Act: -0.1700

Data Index: 224534 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.6304. Min Act: -0.1700

Data Index: 310718 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.5054. Min Act: -0.1700

Data Index: 331443 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.5366. Min Act: -0.1700

Data Index: 53088 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.5366. Min Act: -0.1700

Data Index: 1256510 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.5366. Min Act: -0.1700

Data Index: 823864 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.5366. Min Act: -0.1700

Data Index: 422089 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.4741. Min Act: -0.1700

Data Index: 461439 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.4429. Min Act: -0.1700

Data Index: 2031 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.4429. Min Act: -0.1700

Data Index: 474765 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.4116. Min Act: -0.1700

Data Index: 358272 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.4429. Min Act: -0.1700

Data Index: 1091817 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.4741. Min Act: -0.1700

Data Index: 1231306 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 5.8804. Min Range: -5.8804

Max Act: 5.4429. Min Act: -0.1700

Data Index: 528966 (C4 (Web Text))

Max Activating Token Index: 806