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

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

Neuron 542 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.3221. Min Act: -0.1700

Data Index: 1650051 (Python Code)

Max Activating Token Index: 84

Text #1

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.2750. Min Act: -0.1700

Data Index: 1373103 (Python Code)

Max Activating Token Index: 119

Text #2

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.2907. Min Act: -0.1700

Data Index: 1532561 (Python Code)

Max Activating Token Index: 338

Text #3

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.2592. Min Act: -0.1700

Data Index: 1622756 (Python Code)

Max Activating Token Index: 59

Text #4

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.2592. Min Act: -0.1700

Data Index: 1441340 (Python Code)

Max Activating Token Index: 82

Text #5

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.2750. Min Act: -0.1700

Data Index: 1426044 (Python Code)

Max Activating Token Index: 59

Text #6

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.2435. Min Act: -0.1700

Data Index: 578304 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.1963. Min Act: -0.1700

Data Index: 765367 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.1963. Min Act: -0.1700

Data Index: 721686 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.1963. Min Act: -0.1700

Data Index: 1131258 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.1806. Min Act: -0.1700

Data Index: 505609 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.1806. Min Act: -0.1700

Data Index: 934750 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.2121. Min Act: -0.1700

Data Index: 1380657 (Python Code)

Max Activating Token Index: 73

Text #13

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.1963. Min Act: -0.1700

Data Index: 1565648 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.2121. Min Act: -0.1700

Data Index: 1468316 (Python Code)

Max Activating Token Index: 139

Text #15

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.1963. Min Act: -0.1700

Data Index: 1580365 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.1806. Min Act: -0.1700

Data Index: 1505138 (Python Code)

Max Activating Token Index: 109

Text #17

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.1806. Min Act: -0.1700

Data Index: 1394763 (Python Code)

Max Activating Token Index: 144

Text #18

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.1649. Min Act: -0.1700

Data Index: 1501284 (Python Code)

Max Activating Token Index: 208

Text #19

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.1649. Min Act: -0.1700

Data Index: 1649987 (Python Code)

Max Activating Token Index: 26