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

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

Neuron 2032 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.1164. Min Act: -0.1700

Data Index: 151245 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0690. Min Act: -0.1700

Data Index: 1279546 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0690. Min Act: -0.1700

Data Index: 1356694 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0690. Min Act: -0.1700

Data Index: 615352 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0690. Min Act: -0.1700

Data Index: 1260248 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0375. Min Act: -0.1700

Data Index: 1642511 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0533. Min Act: -0.1700

Data Index: 1251588 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0375. Min Act: -0.1700

Data Index: 1226049 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0375. Min Act: -0.1700

Data Index: 1027678 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0375. Min Act: -0.1700

Data Index: 777711 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0375. Min Act: -0.1700

Data Index: 839807 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0059. Min Act: -0.1700

Data Index: 1261671 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.9901. Min Act: -0.1700

Data Index: 910133 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0375. Min Act: -0.1700

Data Index: 630044 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0217. Min Act: -0.1700

Data Index: 449531 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0059. Min Act: -0.1700

Data Index: 719606 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0217. Min Act: -0.1700

Data Index: 745732 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.9901. Min Act: -0.1700

Data Index: 452048 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.9901. Min Act: -0.1700

Data Index: 91932 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 3.1164. Min Range: -3.1164

Max Act: 3.0059. Min Act: -0.1700

Data Index: 261958 (C4 (Web Text))

Max Activating Token Index: 505