Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1362 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.4754. Min Act: -0.1700

Data Index: 34656 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.4441. Min Act: -0.1700

Data Index: 228091 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.3504. Min Act: -0.1700

Data Index: 1019958 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.3816. Min Act: -0.1700

Data Index: 681070 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.3504. Min Act: -0.1700

Data Index: 1251436 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.3816. Min Act: -0.1700

Data Index: 325940 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.2879. Min Act: -0.1700

Data Index: 888734 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.2254. Min Act: -0.1700

Data Index: 1271516 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.2566. Min Act: -0.1700

Data Index: 1254533 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.2254. Min Act: -0.1700

Data Index: 53671 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.2566. Min Act: -0.1700

Data Index: 965292 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.3191. Min Act: -0.1700

Data Index: 596507 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.2566. Min Act: -0.1700

Data Index: 644502 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.2254. Min Act: -0.1700

Data Index: 661720 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.3191. Min Act: -0.1700

Data Index: 537268 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.2566. Min Act: -0.1700

Data Index: 575625 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.1629. Min Act: -0.1700

Data Index: 777399 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.1941. Min Act: -0.1700

Data Index: 703497 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.2566. Min Act: -0.1700

Data Index: 598416 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 5.4754. Min Range: -5.4754

Max Act: 5.2566. Min Act: -0.1700

Data Index: 1045092 (C4 (Web Text))

Max Activating Token Index: 538