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

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

Neuron 995 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: 5.4423. Min Range: -5.4423

Max Act: 5.4423. Min Act: -0.1700

Data Index: 404709 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 5.4423. Min Range: -5.4423

Max Act: 5.1610. Min Act: -0.1700

Data Index: 1314926 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 5.4423. Min Range: -5.4423

Max Act: 5.0673. Min Act: -0.1700

Data Index: 1019668 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 5.4423. Min Range: -5.4423

Max Act: 5.0673. Min Act: -0.1700

Data Index: 17643 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 5.4423. Min Range: -5.4423

Max Act: 5.0360. Min Act: -0.1700

Data Index: 1256996 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 5.4423. Min Range: -5.4423

Max Act: 5.0360. Min Act: -0.1700

Data Index: 867080 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 5.4423. Min Range: -5.4423

Max Act: 5.0360. Min Act: -0.1700

Data Index: 162591 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 5.4423. Min Range: -5.4423

Max Act: 5.0048. Min Act: -0.1700

Data Index: 658553 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 5.4423. Min Range: -5.4423

Max Act: 4.9735. Min Act: -0.1700

Data Index: 141149 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 5.4423. Min Range: -5.4423

Max Act: 4.9735. Min Act: -0.1699

Data Index: 471638 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 5.4423. Min Range: -5.4423

Max Act: 4.9735. Min Act: -0.1700

Data Index: 255785 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 5.4423. Min Range: -5.4423

Max Act: 4.9110. Min Act: -0.1700

Data Index: 449153 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 5.4423. Min Range: -5.4423

Max Act: 4.9110. Min Act: -0.1700

Data Index: 627080 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 5.4423. Min Range: -5.4423

Max Act: 4.8798. Min Act: -0.1700

Data Index: 1274196 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 5.4423. Min Range: -5.4423

Max Act: 4.9110. Min Act: -0.1700

Data Index: 1276571 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 5.4423. Min Range: -5.4423

Max Act: 4.9110. Min Act: -0.1700

Data Index: 209759 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 5.4423. Min Range: -5.4423

Max Act: 4.8485. Min Act: -0.1700

Data Index: 1269167 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 5.4423. Min Range: -5.4423

Max Act: 4.8485. Min Act: -0.1700

Data Index: 801076 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 5.4423. Min Range: -5.4423

Max Act: 4.8485. Min Act: -0.1700

Data Index: 989651 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 5.4423. Min Range: -5.4423

Max Act: 4.7235. Min Act: -0.1700

Data Index: 78751 (C4 (Web Text))

Max Activating Token Index: 380