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

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

Neuron 749 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: 5.1098. Min Range: -5.1098

Max Act: 5.1098. Min Act: -0.1700

Data Index: 1163293 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 5.1098. Min Range: -5.1098

Max Act: 5.0786. Min Act: -0.1700

Data Index: 229343 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 5.1098. Min Range: -5.1098

Max Act: 5.1098. Min Act: -0.1700

Data Index: 690890 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 5.1098. Min Range: -5.1098

Max Act: 4.9848. Min Act: -0.1700

Data Index: 825965 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 5.1098. Min Range: -5.1098

Max Act: 5.0786. Min Act: -0.1700

Data Index: 1228392 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 5.1098. Min Range: -5.1098

Max Act: 4.9536. Min Act: -0.1700

Data Index: 944723 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 5.1098. Min Range: -5.1098

Max Act: 5.0161. Min Act: -0.1700

Data Index: 199186 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 5.1098. Min Range: -5.1098

Max Act: 4.9848. Min Act: -0.1700

Data Index: 632573 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 5.1098. Min Range: -5.1098

Max Act: 4.9223. Min Act: -0.1700

Data Index: 259239 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 5.1098. Min Range: -5.1098

Max Act: 4.9848. Min Act: -0.1700

Data Index: 1187525 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 5.1098. Min Range: -5.1098

Max Act: 5.0161. Min Act: -0.1700

Data Index: 458702 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 5.1098. Min Range: -5.1098

Max Act: 4.9536. Min Act: -0.1700

Data Index: 76485 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 5.1098. Min Range: -5.1098

Max Act: 4.9536. Min Act: -0.1700

Data Index: 1327266 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 5.1098. Min Range: -5.1098

Max Act: 4.9536. Min Act: -0.1700

Data Index: 887145 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 5.1098. Min Range: -5.1098

Max Act: 4.8598. Min Act: -0.1700

Data Index: 18585 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 5.1098. Min Range: -5.1098

Max Act: 4.8286. Min Act: -0.1700

Data Index: 622687 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 5.1098. Min Range: -5.1098

Max Act: 4.9848. Min Act: -0.1700

Data Index: 1203551 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 5.1098. Min Range: -5.1098

Max Act: 4.9536. Min Act: -0.1700

Data Index: 29134 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 5.1098. Min Range: -5.1098

Max Act: 4.9848. Min Act: -0.1700

Data Index: 837908 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 5.1098. Min Range: -5.1098

Max Act: 4.9223. Min Act: -0.1700

Data Index: 520480 (C4 (Web Text))

Max Activating Token Index: 415