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

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

Neuron 1102 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2881. Min Range: -5.2881

Max Act: 5.2881. Min Act: -0.1700

Data Index: 509561 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 5.2881. Min Range: -5.2881

Max Act: 5.1006. Min Act: -0.1700

Data Index: 143389 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.9443. Min Act: -0.1700

Data Index: 939691 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 5.2881. Min Range: -5.2881

Max Act: 5.0068. Min Act: -0.1700

Data Index: 20135 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.9756. Min Act: -0.1699

Data Index: 1243410 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.9443. Min Act: -0.1699

Data Index: 698856 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.9443. Min Act: -0.1700

Data Index: 1333538 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.9131. Min Act: -0.1700

Data Index: 571271 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.9131. Min Act: -0.1700

Data Index: 327878 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.8818. Min Act: -0.1700

Data Index: 622072 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.9131. Min Act: -0.1700

Data Index: 469007 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.9443. Min Act: -0.1700

Data Index: 1249196 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.8818. Min Act: -0.1699

Data Index: 1190198 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.9131. Min Act: -0.1700

Data Index: 94732 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.7881. Min Act: -0.1700

Data Index: 459969 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.8506. Min Act: -0.1700

Data Index: 506810 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.7568. Min Act: -0.1700

Data Index: 142041 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.8193. Min Act: -0.1700

Data Index: 741375 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.7568. Min Act: -0.1700

Data Index: 1197617 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 5.2881. Min Range: -5.2881

Max Act: 4.7568. Min Act: -0.1700

Data Index: 693340 (C4 (Web Text))

Max Activating Token Index: 586