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

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

Neuron 1779 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: 3.3693. Min Range: -3.3693

Max Act: 3.3693. Min Act: -0.1700

Data Index: 1030669 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.2594. Min Act: -0.1700

Data Index: 110889 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.2123. Min Act: -0.1700

Data Index: 404291 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1965. Min Act: -0.1700

Data Index: 684458 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1965. Min Act: -0.1700

Data Index: 209045 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1808. Min Act: -0.1700

Data Index: 169504 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1808. Min Act: -0.1700

Data Index: 282988 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1808. Min Act: -0.1700

Data Index: 805647 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1493. Min Act: -0.1700

Data Index: 1126790 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1493. Min Act: -0.1700

Data Index: 977031 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1493. Min Act: -0.1700

Data Index: 690409 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1493. Min Act: -0.1700

Data Index: 816759 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1493. Min Act: -0.1700

Data Index: 1145025 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1178. Min Act: -0.1700

Data Index: 358223 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1493. Min Act: -0.1700

Data Index: 243707 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1335. Min Act: -0.1700

Data Index: 392449 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1335. Min Act: -0.1700

Data Index: 299253 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1178. Min Act: -0.1700

Data Index: 1014957 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1178. Min Act: -0.1700

Data Index: 1096434 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.3693. Min Range: -3.3693

Max Act: 3.1178. Min Act: -0.1700

Data Index: 565134 (C4 (Web Text))

Max Activating Token Index: 1023