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

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

Neuron 1016 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1444. Min Range: -5.1444

Max Act: 5.1444. Min Act: -0.1700

Data Index: 529347 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 5.1444. Min Range: -5.1444

Max Act: 5.0194. Min Act: -0.1700

Data Index: 987330 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.8007. Min Act: -0.1700

Data Index: 764349 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.6757. Min Act: -0.1700

Data Index: 301643 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.6757. Min Act: -0.1700

Data Index: 634523 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.5507. Min Act: -0.1700

Data Index: 788633 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.5819. Min Act: -0.1700

Data Index: 760143 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.3319. Min Act: -0.1700

Data Index: 76692 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.5194. Min Act: -0.1700

Data Index: 632816 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.5819. Min Act: -0.1700

Data Index: 169926 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.4569. Min Act: -0.1700

Data Index: 401194 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.5507. Min Act: -0.1700

Data Index: 237560 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.5507. Min Act: -0.1700

Data Index: 1079484 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.4569. Min Act: -0.1700

Data Index: 1325407 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.5507. Min Act: -0.1700

Data Index: 1335912 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.5194. Min Act: -0.1700

Data Index: 1246369 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.4569. Min Act: -0.1700

Data Index: 734556 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.6132. Min Act: -0.1700

Data Index: 627220 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.4569. Min Act: -0.1700

Data Index: 776580 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.4569. Min Act: -0.1700

Data Index: 607066 (C4 (Web Text))

Max Activating Token Index: 122