Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1379 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.9949. Min Act: -0.1700

Data Index: 13642 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.9324. Min Act: -0.1700

Data Index: 537809 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.7449. Min Act: -0.1700

Data Index: 962309 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.6199. Min Act: -0.1699

Data Index: 84254 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.5574. Min Act: -0.1700

Data Index: 912395 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.3074. Min Act: -0.1700

Data Index: 718720 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.4324. Min Act: -0.1700

Data Index: 832646 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.6824. Min Act: -0.1700

Data Index: 722163 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.5574. Min Act: -0.1699

Data Index: 367739 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.6199. Min Act: -0.1700

Data Index: 1100687 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.5574. Min Act: -0.1700

Data Index: 283289 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.5574. Min Act: -0.1700

Data Index: 897047 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.4324. Min Act: -0.1700

Data Index: 446674 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.4949. Min Act: -0.1700

Data Index: 924190 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.3699. Min Act: -0.1700

Data Index: 563579 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.3699. Min Act: -0.1700

Data Index: 773908 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.4949. Min Act: -0.1700

Data Index: 685284 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.1824. Min Act: -0.1699

Data Index: 625634 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.3699. Min Act: -0.1700

Data Index: 679589 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 8.9949. Min Range: -8.9949

Max Act: 8.2449. Min Act: -0.1700

Data Index: 185559 (C4 (Web Text))

Max Activating Token Index: 76