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

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

Neuron 1252 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.4118. Min Act: -0.1700

Data Index: 1000327 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.3490. Min Act: -0.1700

Data Index: 520240 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.3647. Min Act: -0.1700

Data Index: 462017 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.3176. Min Act: -0.1700

Data Index: 1126211 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.3019. Min Act: -0.1700

Data Index: 263873 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.3333. Min Act: -0.1700

Data Index: 249514 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.2862. Min Act: -0.1700

Data Index: 248606 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.3019. Min Act: -0.1700

Data Index: 214458 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.2862. Min Act: -0.1700

Data Index: 1224125 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.2705. Min Act: -0.1700

Data Index: 195919 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.2548. Min Act: -0.1700

Data Index: 112866 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.2548. Min Act: -0.1700

Data Index: 836217 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.2548. Min Act: -0.1700

Data Index: 634744 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.2391. Min Act: -0.1700

Data Index: 390880 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.2391. Min Act: -0.1700

Data Index: 1165986 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.2548. Min Act: -0.1700

Data Index: 847492 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.2548. Min Act: -0.1700

Data Index: 1283936 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.2233. Min Act: -0.1700

Data Index: 425155 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.2548. Min Act: -0.1700

Data Index: 951137 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 3.4118. Min Range: -3.4118

Max Act: 3.2233. Min Act: -0.1700

Data Index: 1280748 (C4 (Web Text))

Max Activating Token Index: 558