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

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

Neuron 1363 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: 5.1331. Min Range: -5.1331

Max Act: 5.1331. Min Act: -0.1700

Data Index: 1232445 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 5.1331. Min Range: -5.1331

Max Act: 5.0393. Min Act: -0.1700

Data Index: 1181833 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 5.1331. Min Range: -5.1331

Max Act: 5.0081. Min Act: -0.1700

Data Index: 634385 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.6018. Min Act: -0.1700

Data Index: 1020976 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.5862. Min Act: -0.1700

Data Index: 43594 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.5549. Min Act: -0.1700

Data Index: 825292 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.4768. Min Act: -0.1700

Data Index: 248875 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.4768. Min Act: -0.1700

Data Index: 917154 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.3987. Min Act: -0.1700

Data Index: 322112 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.4612. Min Act: -0.1700

Data Index: 1005638 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.4143. Min Act: -0.1700

Data Index: 218192 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.4299. Min Act: -0.1700

Data Index: 624347 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.4143. Min Act: -0.1700

Data Index: 776967 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.4299. Min Act: -0.1700

Data Index: 908731 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.4299. Min Act: -0.1700

Data Index: 971180 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.4299. Min Act: -0.1700

Data Index: 1260669 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.4299. Min Act: -0.1700

Data Index: 548828 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.3830. Min Act: -0.1700

Data Index: 407461 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.4299. Min Act: -0.1700

Data Index: 178482 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.4299. Min Act: -0.1700

Data Index: 776515 (C4 (Web Text))

Max Activating Token Index: 402