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

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

Neuron 1458 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: 5.4676. Min Range: -5.4676

Max Act: 5.4676. Min Act: -0.1700

Data Index: 1092457 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 5.4676. Min Range: -5.4676

Max Act: 5.2801. Min Act: -0.1700

Data Index: 1376264 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 5.4676. Min Range: -5.4676

Max Act: 5.1238. Min Act: -0.1700

Data Index: 1431424 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 5.4676. Min Range: -5.4676

Max Act: 5.0301. Min Act: -0.1700

Data Index: 1361454 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.9676. Min Act: -0.1700

Data Index: 1529553 (Python Code)

Max Activating Token Index: 49

Text #5

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.9051. Min Act: -0.1700

Data Index: 1464919 (Python Code)

Max Activating Token Index: 23

Text #6

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.9051. Min Act: -0.1700

Data Index: 1580353 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.9363. Min Act: -0.1700

Data Index: 1409572 (Python Code)

Max Activating Token Index: 61

Text #8

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.9051. Min Act: -0.1700

Data Index: 1542970 (Python Code)

Max Activating Token Index: 178

Text #9

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.8426. Min Act: -0.1700

Data Index: 338268 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.8426. Min Act: -0.1700

Data Index: 1552262 (Python Code)

Max Activating Token Index: 106

Text #11

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.8426. Min Act: -0.1700

Data Index: 1454489 (Python Code)

Max Activating Token Index: 184

Text #12

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.8113. Min Act: -0.1700

Data Index: 1405986 (Python Code)

Max Activating Token Index: 283

Text #13

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.7801. Min Act: -0.1700

Data Index: 1514581 (Python Code)

Max Activating Token Index: 124

Text #14

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.8113. Min Act: -0.1700

Data Index: 1411709 (Python Code)

Max Activating Token Index: 248

Text #15

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.8113. Min Act: -0.1700

Data Index: 1484528 (Python Code)

Max Activating Token Index: 66

Text #16

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.8113. Min Act: -0.1700

Data Index: 677019 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.7801. Min Act: -0.1700

Data Index: 274668 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.8113. Min Act: -0.1700

Data Index: 955436 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 5.4676. Min Range: -5.4676

Max Act: 4.8113. Min Act: -0.1700

Data Index: 945189 (C4 (Web Text))

Max Activating Token Index: 249