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

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

Neuron 1607 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.6919. Min Act: -0.1700

Data Index: 486473 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.2544. Min Act: -0.1700

Data Index: 1348599 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.1919. Min Act: -0.1700

Data Index: 1197962 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.1606. Min Act: -0.1700

Data Index: 328237 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.1919. Min Act: -0.1700

Data Index: 1025306 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.1606. Min Act: -0.1700

Data Index: 244414 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.1606. Min Act: -0.1700

Data Index: 203645 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.1294. Min Act: -0.1700

Data Index: 933912 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.0981. Min Act: -0.1700

Data Index: 1138361 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.1294. Min Act: -0.1700

Data Index: 1168026 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.0981. Min Act: -0.1700

Data Index: 368039 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.0669. Min Act: -0.1700

Data Index: 35622 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.0669. Min Act: -0.1700

Data Index: 401063 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.0669. Min Act: -0.1700

Data Index: 513181 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.0044. Min Act: -0.1700

Data Index: 906476 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.0356. Min Act: -0.1700

Data Index: 730845 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.0669. Min Act: -0.1700

Data Index: 209626 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 5.6919. Min Range: -5.6919

Max Act: 5.0044. Min Act: -0.1700

Data Index: 579948 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 5.6919. Min Range: -5.6919

Max Act: 4.9731. Min Act: -0.1700

Data Index: 263205 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 5.6919. Min Range: -5.6919

Max Act: 4.9731. Min Act: -0.1700

Data Index: 1175102 (C4 (Web Text))

Max Activating Token Index: 426