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

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

Neuron 967 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.3022. Min Act: -0.1700

Data Index: 1004065 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.3334. Min Act: -0.1700

Data Index: 748900 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.2084. Min Act: -0.1700

Data Index: 759071 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.2709. Min Act: -0.1700

Data Index: 425874 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.1459. Min Act: -0.1700

Data Index: 170866 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.1772. Min Act: -0.1700

Data Index: 1192451 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.1772. Min Act: -0.1700

Data Index: 1330217 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.1147. Min Act: -0.1700

Data Index: 349927 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.0834. Min Act: -0.1700

Data Index: 812706 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.1147. Min Act: -0.1700

Data Index: 265827 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.0834. Min Act: -0.1700

Data Index: 343341 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.0209. Min Act: -0.1700

Data Index: 815566 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.0834. Min Act: -0.1700

Data Index: 793541 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.0834. Min Act: -0.1700

Data Index: 105390 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.0209. Min Act: -0.1700

Data Index: 1067384 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.0522. Min Act: -0.1700

Data Index: 30662 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.0209. Min Act: -0.1700

Data Index: 635889 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 5.3334. Min Range: -5.3334

Max Act: 4.9897. Min Act: -0.1700

Data Index: 600775 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.0522. Min Act: -0.1700

Data Index: 857986 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 5.3334. Min Range: -5.3334

Max Act: 5.0209. Min Act: -0.1700

Data Index: 556580 (C4 (Web Text))

Max Activating Token Index: 639