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

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

Neuron 368 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.9222. Min Act: -0.1700

Data Index: 1599005 (Python Code)

Max Activating Token Index: 99

Text #1

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7658. Min Act: -0.1700

Data Index: 330639 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7502. Min Act: -0.1700

Data Index: 1463266 (Python Code)

Max Activating Token Index: 418

Text #3

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7502. Min Act: -0.1700

Data Index: 1330292 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7502. Min Act: -0.1700

Data Index: 1460843 (Python Code)

Max Activating Token Index: 17

Text #5

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7502. Min Act: -0.1700

Data Index: 1650883 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7345. Min Act: -0.1700

Data Index: 1363246 (Python Code)

Max Activating Token Index: 151

Text #7

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7345. Min Act: -0.1700

Data Index: 1042863 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7971. Min Act: -0.1700

Data Index: 971248 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7189. Min Act: -0.1700

Data Index: 361700 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.6876. Min Act: -0.1700

Data Index: 1497099 (Python Code)

Max Activating Token Index: 127

Text #11

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7345. Min Act: -0.1700

Data Index: 1566341 (Python Code)

Max Activating Token Index: 730

Text #12

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7345. Min Act: -0.1700

Data Index: 1485840 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7189. Min Act: -0.1700

Data Index: 377654 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7032. Min Act: -0.1700

Data Index: 906964 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7345. Min Act: -0.1700

Data Index: 705486 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7345. Min Act: -0.1700

Data Index: 531885 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7345. Min Act: -0.1700

Data Index: 748202 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7345. Min Act: -0.1700

Data Index: 1562710 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.6720. Min Act: -0.1700

Data Index: 1057371 (C4 (Web Text))

Max Activating Token Index: 818