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

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

Neuron 250 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: 7.7941. Min Range: -7.7941

Max Act: 7.7941. Min Act: -0.1697

Data Index: 775484 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.5441. Min Act: -0.1700

Data Index: 730894 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.6066. Min Act: -0.1699

Data Index: 153835 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.4816. Min Act: -0.1699

Data Index: 702373 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.4191. Min Act: -0.1700

Data Index: 834302 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.3566. Min Act: -0.1700

Data Index: 587456 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.3566. Min Act: -0.1700

Data Index: 398294 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.3566. Min Act: -0.1700

Data Index: 1325717 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.3566. Min Act: -0.1700

Data Index: 748950 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.2941. Min Act: -0.1699

Data Index: 1145478 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.3566. Min Act: -0.1700

Data Index: 1196224 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.2941. Min Act: -0.1700

Data Index: 277160 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.1691. Min Act: -0.1700

Data Index: 1072830 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.2316. Min Act: -0.1700

Data Index: 139991 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.2941. Min Act: -0.1700

Data Index: 1155850 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.2316. Min Act: -0.1700

Data Index: 1059066 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.2316. Min Act: -0.1700

Data Index: 788881 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.1691. Min Act: -0.1700

Data Index: 687433 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.1691. Min Act: -0.1700

Data Index: 363275 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 7.7941. Min Range: -7.7941

Max Act: 7.1691. Min Act: -0.1700

Data Index: 1183550 (C4 (Web Text))

Max Activating Token Index: 73