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

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

Neuron 1677 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.3999. Min Act: -0.1700

Data Index: 296367 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.2115. Min Act: -0.1700

Data Index: 273861 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.1800. Min Act: -0.1700

Data Index: 1191106 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.1800. Min Act: -0.1700

Data Index: 751229 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.1800. Min Act: -0.1700

Data Index: 1348744 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.1170. Min Act: -0.1700

Data Index: 418608 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.1485. Min Act: -0.1700

Data Index: 886579 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.1485. Min Act: -0.1700

Data Index: 733568 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.1328. Min Act: -0.1700

Data Index: 167422 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.1170. Min Act: -0.1700

Data Index: 1109149 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.1012. Min Act: -0.1700

Data Index: 661110 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.0855. Min Act: -0.1700

Data Index: 1039461 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.0697. Min Act: -0.1700

Data Index: 930339 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.0539. Min Act: -0.1700

Data Index: 931505 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.1012. Min Act: -0.1700

Data Index: 746442 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.0697. Min Act: -0.1700

Data Index: 277887 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.0697. Min Act: -0.1700

Data Index: 561249 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.0697. Min Act: -0.1700

Data Index: 1126361 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.0697. Min Act: -0.1700

Data Index: 332356 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 3.3999. Min Range: -3.3999

Max Act: 3.0855. Min Act: -0.1700

Data Index: 37642 (C4 (Web Text))

Max Activating Token Index: 838