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

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

Neuron 31 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1010. Min Range: -7.1010

Max Act: 7.1010. Min Act: -0.1700

Data Index: 1101923 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.8510. Min Act: -0.1699

Data Index: 853963 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.7572. Min Act: -0.1697

Data Index: 570758 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.6947. Min Act: -0.1699

Data Index: 974833 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.6322. Min Act: -0.1699

Data Index: 551575 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.6322. Min Act: -0.1700

Data Index: 749935 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.6010. Min Act: -0.1699

Data Index: 199006 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.5697. Min Act: -0.1699

Data Index: 1255933 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.5697. Min Act: -0.1700

Data Index: 1321409 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.5072. Min Act: -0.1699

Data Index: 700387 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.5385. Min Act: -0.1700

Data Index: 1213514 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.5385. Min Act: -0.1700

Data Index: 1324309 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.5072. Min Act: -0.1699

Data Index: 1062265 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.5697. Min Act: -0.1700

Data Index: 1061573 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.5072. Min Act: -0.1700

Data Index: 5259 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.5385. Min Act: -0.1700

Data Index: 442955 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.5385. Min Act: -0.1700

Data Index: 770257 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.5072. Min Act: -0.1700

Data Index: 161291 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.5385. Min Act: -0.1700

Data Index: 433840 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 7.1010. Min Range: -7.1010

Max Act: 6.5072. Min Act: -0.1700

Data Index: 1286735 (C4 (Web Text))

Max Activating Token Index: 484