Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1212 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.4380. Min Act: -0.1700

Data Index: 794912 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.4067. Min Act: -0.1700

Data Index: 1086867 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.2817. Min Act: -0.1700

Data Index: 1051733 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.2505. Min Act: -0.1699

Data Index: 1325379 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.1567. Min Act: -0.1700

Data Index: 99122 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.1567. Min Act: -0.1700

Data Index: 33911 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.0630. Min Act: -0.1700

Data Index: 406311 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.0630. Min Act: -0.1700

Data Index: 1305225 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.0942. Min Act: -0.1700

Data Index: 1101882 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.1880. Min Act: -0.1700

Data Index: 608657 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.0942. Min Act: -0.1700

Data Index: 791247 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.1255. Min Act: -0.1700

Data Index: 896920 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.0942. Min Act: -0.1700

Data Index: 91152 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.0942. Min Act: -0.1700

Data Index: 648267 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.0942. Min Act: -0.1700

Data Index: 98929 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.0317. Min Act: -0.1700

Data Index: 918760 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.1255. Min Act: -0.1700

Data Index: 1103473 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.0942. Min Act: -0.1700

Data Index: 1006734 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.0317. Min Act: -0.1700

Data Index: 1293730 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 5.4380. Min Range: -5.4380

Max Act: 5.0942. Min Act: -0.1700

Data Index: 388731 (C4 (Web Text))

Max Activating Token Index: 5