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

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

Neuron 409 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: 5.9138. Min Range: -5.9138

Max Act: 5.9138. Min Act: -0.1700

Data Index: 1295209 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.7419. Min Act: -0.1700

Data Index: 717741 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.6950. Min Act: -0.1699

Data Index: 1030787 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.6482. Min Act: -0.1699

Data Index: 623156 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.6638. Min Act: -0.1700

Data Index: 389775 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.6013. Min Act: -0.1700

Data Index: 995869 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.6013. Min Act: -0.1700

Data Index: 860872 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.5700. Min Act: -0.1700

Data Index: 1234605 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.6013. Min Act: -0.1700

Data Index: 185054 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.5857. Min Act: -0.1700

Data Index: 1104493 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.5857. Min Act: -0.1700

Data Index: 658152 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.5544. Min Act: -0.1700

Data Index: 818246 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.5700. Min Act: -0.1700

Data Index: 1008946 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.5388. Min Act: -0.1700

Data Index: 1016552 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.5700. Min Act: -0.1700

Data Index: 455026 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.5388. Min Act: -0.1700

Data Index: 189147 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.5388. Min Act: -0.1700

Data Index: 620468 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.5232. Min Act: -0.1700

Data Index: 1308566 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.5232. Min Act: -0.1700

Data Index: 80886 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 5.9138. Min Range: -5.9138

Max Act: 5.5075. Min Act: -0.1700

Data Index: 698165 (C4 (Web Text))

Max Activating Token Index: 161