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

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

Neuron 1054 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0309. Min Range: -4.0309

Max Act: 4.0309. Min Act: -0.1700

Data Index: 1090074 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.9058. Min Act: -0.1700

Data Index: 106283 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.5616. Min Act: -0.1700

Data Index: 1569410 (Python Code)

Max Activating Token Index: 446

Text #3

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.5302. Min Act: -0.1700

Data Index: 617511 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.5616. Min Act: -0.1700

Data Index: 617996 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.5929. Min Act: -0.1700

Data Index: 959989 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.5302. Min Act: -0.1700

Data Index: 234769 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.5302. Min Act: -0.1700

Data Index: 72975 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.5302. Min Act: -0.1700

Data Index: 478667 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.4989. Min Act: -0.1700

Data Index: 6917 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.4676. Min Act: -0.1700

Data Index: 1071694 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.4048. Min Act: -0.1700

Data Index: 1345299 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.4362. Min Act: -0.1700

Data Index: 430285 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.4362. Min Act: -0.1700

Data Index: 52081 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.4676. Min Act: -0.1700

Data Index: 383016 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.4048. Min Act: -0.1700

Data Index: 1002259 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.4362. Min Act: -0.1700

Data Index: 107872 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.4362. Min Act: -0.1700

Data Index: 365927 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.4048. Min Act: -0.1700

Data Index: 1573847 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.3421. Min Act: -0.1700

Data Index: 1414728 (Python Code)

Max Activating Token Index: 597