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

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

Neuron 505 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1064. Min Range: -3.1064

Max Act: 3.1064. Min Act: -0.1700

Data Index: 374588 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 3.1064. Min Range: -3.1064

Max Act: 3.0907. Min Act: -0.1700

Data Index: 1206677 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 3.1064. Min Range: -3.1064

Max Act: 3.0749. Min Act: -0.1700

Data Index: 238984 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 3.1064. Min Range: -3.1064

Max Act: 3.0433. Min Act: -0.1700

Data Index: 1256470 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 3.1064. Min Range: -3.1064

Max Act: 3.0591. Min Act: -0.1700

Data Index: 716454 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9959. Min Act: -0.1700

Data Index: 231055 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9643. Min Act: -0.1700

Data Index: 870657 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9485. Min Act: -0.1700

Data Index: 1199394 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9485. Min Act: -0.1700

Data Index: 982501 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9485. Min Act: -0.1700

Data Index: 1048437 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9485. Min Act: -0.1700

Data Index: 753895 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9485. Min Act: -0.1700

Data Index: 428432 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9168. Min Act: -0.1700

Data Index: 749052 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9326. Min Act: -0.1700

Data Index: 1172538 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9168. Min Act: -0.1700

Data Index: 1244566 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9168. Min Act: -0.1700

Data Index: 835647 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9009. Min Act: -0.1700

Data Index: 305360 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9168. Min Act: -0.1700

Data Index: 290388 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9009. Min Act: -0.1700

Data Index: 1095603 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 3.1064. Min Range: -3.1064

Max Act: 2.9168. Min Act: -0.1700

Data Index: 314514 (C4 (Web Text))

Max Activating Token Index: 595