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

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

Neuron 985 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: 5.2831. Min Range: -5.2831

Max Act: 5.1894. Min Act: -0.1700

Data Index: 1199731 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 5.2831. Min Range: -5.2831

Max Act: 5.2831. Min Act: -0.1700

Data Index: 807053 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 5.2831. Min Range: -5.2831

Max Act: 5.1581. Min Act: -0.1700

Data Index: 1059502 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 5.2831. Min Range: -5.2831

Max Act: 5.1581. Min Act: -0.1700

Data Index: 1183449 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 5.2831. Min Range: -5.2831

Max Act: 5.1581. Min Act: -0.1700

Data Index: 457418 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 5.2831. Min Range: -5.2831

Max Act: 5.1269. Min Act: -0.1700

Data Index: 1333738 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 5.2831. Min Range: -5.2831

Max Act: 5.0956. Min Act: -0.1700

Data Index: 274098 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 5.2831. Min Range: -5.2831

Max Act: 5.0956. Min Act: -0.1700

Data Index: 1051194 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 5.2831. Min Range: -5.2831

Max Act: 5.0019. Min Act: -0.1700

Data Index: 576799 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 5.2831. Min Range: -5.2831

Max Act: 5.0331. Min Act: -0.1700

Data Index: 1308721 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 5.2831. Min Range: -5.2831

Max Act: 5.0019. Min Act: -0.1700

Data Index: 1322311 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 5.2831. Min Range: -5.2831

Max Act: 4.9394. Min Act: -0.1700

Data Index: 994115 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 5.2831. Min Range: -5.2831

Max Act: 4.9706. Min Act: -0.1700

Data Index: 570819 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 5.2831. Min Range: -5.2831

Max Act: 4.9706. Min Act: -0.1700

Data Index: 490245 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 5.2831. Min Range: -5.2831

Max Act: 4.9394. Min Act: -0.1700

Data Index: 332874 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 5.2831. Min Range: -5.2831

Max Act: 4.9394. Min Act: -0.1700

Data Index: 1053149 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 5.2831. Min Range: -5.2831

Max Act: 4.8769. Min Act: -0.1700

Data Index: 502994 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 5.2831. Min Range: -5.2831

Max Act: 4.8769. Min Act: -0.1700

Data Index: 1305095 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 5.2831. Min Range: -5.2831

Max Act: 4.9081. Min Act: -0.1700

Data Index: 714813 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 5.2831. Min Range: -5.2831

Max Act: 4.9081. Min Act: -0.1700

Data Index: 1326622 (C4 (Web Text))

Max Activating Token Index: 967