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

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

Neuron 31 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0846. Min Range: -7.0846

Max Act: 7.0846. Min Act: -0.1700

Data Index: 357814 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.3659. Min Act: -0.1700

Data Index: 431521 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.1471. Min Act: -0.1700

Data Index: 13771 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.1159. Min Act: -0.1700

Data Index: 523008 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.0534. Min Act: -0.1700

Data Index: 258252 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.0221. Min Act: -0.1700

Data Index: 897197 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 7.0846. Min Range: -7.0846

Max Act: 5.9596. Min Act: -0.1700

Data Index: 301435 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 7.0846. Min Range: -7.0846

Max Act: 5.9284. Min Act: -0.1700

Data Index: 156427 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 7.0846. Min Range: -7.0846

Max Act: 5.8971. Min Act: -0.1700

Data Index: 1646090 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 7.0846. Min Range: -7.0846

Max Act: 5.9284. Min Act: -0.1700

Data Index: 1210311 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 7.0846. Min Range: -7.0846

Max Act: 5.9284. Min Act: -0.1700

Data Index: 496158 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 7.0846. Min Range: -7.0846

Max Act: 5.8659. Min Act: -0.1700

Data Index: 478167 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 7.0846. Min Range: -7.0846

Max Act: 5.8659. Min Act: -0.1700

Data Index: 743579 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 7.0846. Min Range: -7.0846

Max Act: 5.8659. Min Act: -0.1700

Data Index: 1071554 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 7.0846. Min Range: -7.0846

Max Act: 5.8659. Min Act: -0.1700

Data Index: 13656 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 7.0846. Min Range: -7.0846

Max Act: 5.8971. Min Act: -0.1699

Data Index: 1593197 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 7.0846. Min Range: -7.0846

Max Act: 5.8346. Min Act: -0.1700

Data Index: 762121 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 7.0846. Min Range: -7.0846

Max Act: 5.8659. Min Act: -0.1700

Data Index: 654702 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 7.0846. Min Range: -7.0846

Max Act: 5.8346. Min Act: -0.1700

Data Index: 593913 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 7.0846. Min Range: -7.0846

Max Act: 5.8034. Min Act: -0.1700

Data Index: 735895 (C4 (Web Text))

Max Activating Token Index: 825