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

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

Neuron 497 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: 7.3680. Min Range: -7.3680

Max Act: 7.3680. Min Act: -0.1700

Data Index: 454750 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 7.3680. Min Range: -7.3680

Max Act: 7.0242. Min Act: -0.1700

Data Index: 611368 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.9930. Min Act: -0.1700

Data Index: 39247 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.8992. Min Act: -0.1700

Data Index: 1035206 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.9617. Min Act: -0.1700

Data Index: 781156 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.9305. Min Act: -0.1700

Data Index: 1076827 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.8055. Min Act: -0.1700

Data Index: 268570 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.9305. Min Act: -0.1700

Data Index: 351492 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.7430. Min Act: -0.1700

Data Index: 1329463 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.8055. Min Act: -0.1700

Data Index: 1064115 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.8680. Min Act: -0.1700

Data Index: 87312 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.7742. Min Act: -0.1700

Data Index: 210607 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.6492. Min Act: -0.1700

Data Index: 695428 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.7117. Min Act: -0.1700

Data Index: 997908 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.7117. Min Act: -0.1700

Data Index: 1309756 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.7430. Min Act: -0.1700

Data Index: 850599 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.6805. Min Act: -0.1700

Data Index: 992373 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.5867. Min Act: -0.1700

Data Index: 94606 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.6805. Min Act: -0.1700

Data Index: 972737 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 7.3680. Min Range: -7.3680

Max Act: 6.6180. Min Act: -0.1700

Data Index: 567990 (C4 (Web Text))

Max Activating Token Index: 354