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

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

Neuron 760 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: 5.3835. Min Range: -5.3835

Max Act: 5.3835. Min Act: -0.1700

Data Index: 242310 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 5.3835. Min Range: -5.3835

Max Act: 5.2585. Min Act: -0.1700

Data Index: 623061 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 5.3835. Min Range: -5.3835

Max Act: 5.2585. Min Act: -0.1700

Data Index: 649769 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 5.3835. Min Range: -5.3835

Max Act: 5.2585. Min Act: -0.1700

Data Index: 1336220 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 5.3835. Min Range: -5.3835

Max Act: 5.1960. Min Act: -0.1700

Data Index: 7592 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 5.3835. Min Range: -5.3835

Max Act: 4.9773. Min Act: -0.1700

Data Index: 1045509 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 5.3835. Min Range: -5.3835

Max Act: 5.0085. Min Act: -0.1700

Data Index: 1087110 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 5.3835. Min Range: -5.3835

Max Act: 5.0398. Min Act: -0.1700

Data Index: 58129 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 5.3835. Min Range: -5.3835

Max Act: 5.0085. Min Act: -0.1700

Data Index: 832070 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 5.3835. Min Range: -5.3835

Max Act: 4.9773. Min Act: -0.1700

Data Index: 832676 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 5.3835. Min Range: -5.3835

Max Act: 4.9460. Min Act: -0.1700

Data Index: 960314 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 5.3835. Min Range: -5.3835

Max Act: 5.0085. Min Act: -0.1700

Data Index: 1285605 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 5.3835. Min Range: -5.3835

Max Act: 4.9773. Min Act: -0.1700

Data Index: 1199827 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 5.3835. Min Range: -5.3835

Max Act: 4.9460. Min Act: -0.1700

Data Index: 982934 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 5.3835. Min Range: -5.3835

Max Act: 4.9460. Min Act: -0.1700

Data Index: 292591 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 5.3835. Min Range: -5.3835

Max Act: 4.9460. Min Act: -0.1700

Data Index: 289620 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 5.3835. Min Range: -5.3835

Max Act: 4.8835. Min Act: -0.1700

Data Index: 1149362 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 5.3835. Min Range: -5.3835

Max Act: 4.9460. Min Act: -0.1700

Data Index: 497480 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 5.3835. Min Range: -5.3835

Max Act: 4.9773. Min Act: -0.1700

Data Index: 286852 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 5.3835. Min Range: -5.3835

Max Act: 4.9148. Min Act: -0.1700

Data Index: 1039904 (C4 (Web Text))

Max Activating Token Index: 442