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

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

Neuron 104 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: 5.8979. Min Range: -5.8979

Max Act: 5.8979. Min Act: -0.1700

Data Index: 762538 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.8354. Min Act: -0.1700

Data Index: 649025 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.8667. Min Act: -0.1700

Data Index: 571178 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.8667. Min Act: -0.1700

Data Index: 902213 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.8042. Min Act: -0.1700

Data Index: 1145972 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.8042. Min Act: -0.1700

Data Index: 106286 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.8042. Min Act: -0.1700

Data Index: 896351 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.8042. Min Act: -0.1700

Data Index: 457003 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.7417. Min Act: -0.1700

Data Index: 693794 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.7729. Min Act: -0.1700

Data Index: 831303 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.7729. Min Act: -0.1700

Data Index: 766685 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.7104. Min Act: -0.1700

Data Index: 493849 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.7417. Min Act: -0.1700

Data Index: 1207531 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.6792. Min Act: -0.1700

Data Index: 1117946 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.7104. Min Act: -0.1700

Data Index: 652468 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.7417. Min Act: -0.1700

Data Index: 991408 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.7104. Min Act: -0.1700

Data Index: 442877 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.6792. Min Act: -0.1700

Data Index: 563149 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.6479. Min Act: -0.1700

Data Index: 812861 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 5.8979. Min Range: -5.8979

Max Act: 5.7104. Min Act: -0.1700

Data Index: 642213 (C4 (Web Text))

Max Activating Token Index: 134