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

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

Neuron 764 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: 5.2907. Min Range: -5.2907

Max Act: 5.2907. Min Act: -0.1700

Data Index: 746215 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.1969. Min Act: -0.1700

Data Index: 849809 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.1500. Min Act: -0.1700

Data Index: 22785 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.0407. Min Act: -0.1700

Data Index: 1006835 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.1657. Min Act: -0.1700

Data Index: 331036 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.1344. Min Act: -0.1700

Data Index: 959743 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.0875. Min Act: -0.1700

Data Index: 1304028 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.1032. Min Act: -0.1700

Data Index: 572030 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.0094. Min Act: -0.1700

Data Index: 556881 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.0563. Min Act: -0.1700

Data Index: 312443 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.0719. Min Act: -0.1700

Data Index: 398613 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.0407. Min Act: -0.1700

Data Index: 272312 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.0563. Min Act: -0.1700

Data Index: 1000017 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.0250. Min Act: -0.1700

Data Index: 3396 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.0719. Min Act: -0.1700

Data Index: 275691 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.0250. Min Act: -0.1700

Data Index: 109145 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 5.2907. Min Range: -5.2907

Max Act: 4.9938. Min Act: -0.1700

Data Index: 1289027 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.0407. Min Act: -0.1700

Data Index: 273551 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 5.2907. Min Range: -5.2907

Max Act: 4.9625. Min Act: -0.1700

Data Index: 682894 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 5.2907. Min Range: -5.2907

Max Act: 5.0250. Min Act: -0.1700

Data Index: 105689 (C4 (Web Text))

Max Activating Token Index: 70