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

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

Neuron 1510 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.8191. Min Act: -0.1700

Data Index: 1251790 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.7252. Min Act: -0.1700

Data Index: 959835 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.7252. Min Act: -0.1700

Data Index: 481641 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.6470. Min Act: -0.1700

Data Index: 782379 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.6783. Min Act: -0.1700

Data Index: 890022 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.6470. Min Act: -0.1700

Data Index: 467044 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.6470. Min Act: -0.1700

Data Index: 1154309 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.6157. Min Act: -0.1700

Data Index: 1028316 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.6000. Min Act: -0.1700

Data Index: 1112526 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.5844. Min Act: -0.1700

Data Index: 1157247 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.6000. Min Act: -0.1700

Data Index: 494783 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.5844. Min Act: -0.1700

Data Index: 485606 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.6000. Min Act: -0.1700

Data Index: 3401 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.5687. Min Act: -0.1700

Data Index: 47825 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.5687. Min Act: -0.1700

Data Index: 439673 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.5687. Min Act: -0.1700

Data Index: 149216 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.5687. Min Act: -0.1700

Data Index: 739963 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.5844. Min Act: -0.1700

Data Index: 1134101 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.5844. Min Act: -0.1700

Data Index: 1349992 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 3.8191. Min Range: -3.8191

Max Act: 3.5687. Min Act: -0.1700

Data Index: 248044 (C4 (Web Text))

Max Activating Token Index: 624