Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 766 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4007. Min Range: -5.4007

Max Act: 5.4007. Min Act: -0.1700

Data Index: 1484666 (Python Code)

Max Activating Token Index: 872

Text #1

Max Range: 5.4007. Min Range: -5.4007

Max Act: 5.2444. Min Act: -0.1700

Data Index: 1552312 (Python Code)

Max Activating Token Index: 987

Text #2

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.9632. Min Act: -0.1700

Data Index: 1594956 (Python Code)

Max Activating Token Index: 315

Text #3

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.9319. Min Act: -0.1699

Data Index: 1575207 (Python Code)

Max Activating Token Index: 412

Text #4

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.9319. Min Act: -0.1700

Data Index: 1571939 (Python Code)

Max Activating Token Index: 788

Text #5

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.9007. Min Act: -0.1700

Data Index: 1583755 (Python Code)

Max Activating Token Index: 410

Text #6

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.8382. Min Act: -0.1700

Data Index: 1494578 (Python Code)

Max Activating Token Index: 294

Text #7

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.8694. Min Act: -0.1700

Data Index: 1559306 (Python Code)

Max Activating Token Index: 123

Text #8

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.8694. Min Act: -0.1700

Data Index: 1507368 (Python Code)

Max Activating Token Index: 228

Text #9

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.8382. Min Act: -0.1699

Data Index: 1624387 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.8069. Min Act: -0.1700

Data Index: 1396974 (Python Code)

Max Activating Token Index: 215

Text #11

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.9007. Min Act: -0.1700

Data Index: 1438374 (Python Code)

Max Activating Token Index: 58

Text #12

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.8694. Min Act: -0.1700

Data Index: 1523664 (Python Code)

Max Activating Token Index: 653

Text #13

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.8382. Min Act: -0.1700

Data Index: 1616915 (Python Code)

Max Activating Token Index: 127

Text #14

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.8694. Min Act: -0.1700

Data Index: 1652357 (Python Code)

Max Activating Token Index: 554

Text #15

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.8382. Min Act: -0.1700

Data Index: 1627927 (Python Code)

Max Activating Token Index: 673

Text #16

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.8069. Min Act: -0.1700

Data Index: 1576279 (Python Code)

Max Activating Token Index: 1005

Text #17

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.7444. Min Act: -0.1700

Data Index: 1573728 (Python Code)

Max Activating Token Index: 546

Text #18

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.8069. Min Act: -0.1700

Data Index: 1377175 (Python Code)

Max Activating Token Index: 622

Text #19

Max Range: 5.4007. Min Range: -5.4007

Max Act: 4.8382. Min Act: -0.1699

Data Index: 1568902 (Python Code)

Max Activating Token Index: 464