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

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

Neuron 889 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.5118. Min Act: -0.1700

Data Index: 388493 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.4493. Min Act: -0.1700

Data Index: 234114 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.3868. Min Act: -0.1700

Data Index: 935101 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.2618. Min Act: -0.1700

Data Index: 872826 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.2618. Min Act: -0.1700

Data Index: 9336 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.2930. Min Act: -0.1700

Data Index: 1317142 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.3555. Min Act: -0.1700

Data Index: 1162901 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.2930. Min Act: -0.1700

Data Index: 991170 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.2305. Min Act: -0.1700

Data Index: 934027 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.2930. Min Act: -0.1700

Data Index: 609092 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.1680. Min Act: -0.1700

Data Index: 1203284 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.1993. Min Act: -0.1700

Data Index: 786933 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.1055. Min Act: -0.1700

Data Index: 649810 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.1680. Min Act: -0.1700

Data Index: 842055 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.1680. Min Act: -0.1700

Data Index: 1114650 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.1055. Min Act: -0.1700

Data Index: 1330444 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.1993. Min Act: -0.1700

Data Index: 195429 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.1368. Min Act: -0.1700

Data Index: 1191779 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.0430. Min Act: -0.1700

Data Index: 11001 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 5.5118. Min Range: -5.5118

Max Act: 5.1680. Min Act: -0.1700

Data Index: 53471 (C4 (Web Text))

Max Activating Token Index: 61