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

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

Neuron 1521 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: 3.6365. Min Range: -3.6365

Max Act: 3.6365. Min Act: -0.1700

Data Index: 1245641 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4329. Min Act: -0.1700

Data Index: 1210509 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4015. Min Act: -0.1700

Data Index: 272517 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4329. Min Act: -0.1700

Data Index: 233690 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4172. Min Act: -0.1700

Data Index: 45539 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3858. Min Act: -0.1700

Data Index: 55792 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3387. Min Act: -0.1700

Data Index: 337579 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3858. Min Act: -0.1700

Data Index: 915414 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3387. Min Act: -0.1700

Data Index: 1237355 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3387. Min Act: -0.1700

Data Index: 1342828 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3073. Min Act: -0.1700

Data Index: 52627 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3544. Min Act: -0.1700

Data Index: 771131 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3230. Min Act: -0.1700

Data Index: 1165170 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3073. Min Act: -0.1700

Data Index: 359599 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.2916. Min Act: -0.1700

Data Index: 41868 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3073. Min Act: -0.1700

Data Index: 619185 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.2759. Min Act: -0.1700

Data Index: 387799 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3073. Min Act: -0.1700

Data Index: 45054 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.2916. Min Act: -0.1700

Data Index: 1047676 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.3073. Min Act: -0.1700

Data Index: 131541 (C4 (Web Text))

Max Activating Token Index: 724