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

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

Neuron 254 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: 5.3157. Min Range: -5.3157

Max Act: 5.3157. Min Act: -0.1700

Data Index: 746354 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.3157. Min Act: -0.1700

Data Index: 725931 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.2532. Min Act: -0.1700

Data Index: 817098 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.2532. Min Act: -0.1700

Data Index: 761674 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.2532. Min Act: -0.1700

Data Index: 617385 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.2220. Min Act: -0.1700

Data Index: 694785 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.3157. Min Act: -0.1700

Data Index: 123372 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.2845. Min Act: -0.1700

Data Index: 1241994 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.2845. Min Act: -0.1700

Data Index: 473190 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.1907. Min Act: -0.1700

Data Index: 740772 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.2220. Min Act: -0.1700

Data Index: 1291462 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.1595. Min Act: -0.1700

Data Index: 1303803 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.1907. Min Act: -0.1700

Data Index: 366746 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.1282. Min Act: -0.1700

Data Index: 935902 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.1907. Min Act: -0.1700

Data Index: 1178081 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.1595. Min Act: -0.1700

Data Index: 174239 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.2532. Min Act: -0.1700

Data Index: 1070285 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.2220. Min Act: -0.1700

Data Index: 144017 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.1907. Min Act: -0.1700

Data Index: 345678 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 5.3157. Min Range: -5.3157

Max Act: 5.1595. Min Act: -0.1700

Data Index: 163034 (C4 (Web Text))

Max Activating Token Index: 824