Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1443 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.9974. Min Act: -0.1700

Data Index: 428019 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.9348. Min Act: -0.1700

Data Index: 404832 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.9036. Min Act: -0.1700

Data Index: 797411 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.7315. Min Act: -0.1700

Data Index: 281535 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.7315. Min Act: -0.1700

Data Index: 1192504 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.7785. Min Act: -0.1700

Data Index: 231181 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.7785. Min Act: -0.1700

Data Index: 969045 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.7785. Min Act: -0.1700

Data Index: 847412 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.7472. Min Act: -0.1700

Data Index: 12028 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.7472. Min Act: -0.1700

Data Index: 916933 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.7159. Min Act: -0.1700

Data Index: 139967 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.7315. Min Act: -0.1700

Data Index: 1260225 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.7159. Min Act: -0.1700

Data Index: 970296 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.7472. Min Act: -0.1700

Data Index: 1277836 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.7315. Min Act: -0.1700

Data Index: 674424 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.7159. Min Act: -0.1700

Data Index: 1337229 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.7159. Min Act: -0.1700

Data Index: 526071 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.6689. Min Act: -0.1700

Data Index: 920605 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.6846. Min Act: -0.1700

Data Index: 903444 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 3.9974. Min Range: -3.9974

Max Act: 3.7002. Min Act: -0.1700

Data Index: 718447 (C4 (Web Text))

Max Activating Token Index: 134