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

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

Neuron 1927 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.6672. Min Act: -0.1700

Data Index: 485065 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.6202. Min Act: -0.1700

Data Index: 943541 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.6202. Min Act: -0.1700

Data Index: 1114824 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.6358. Min Act: -0.1700

Data Index: 470664 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.6985. Min Act: -0.1700

Data Index: 829618 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.6672. Min Act: -0.1700

Data Index: 668106 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.6515. Min Act: -0.1700

Data Index: 889499 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.6202. Min Act: -0.1700

Data Index: 281385 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5732. Min Act: -0.1700

Data Index: 1210368 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.6202. Min Act: -0.1700

Data Index: 276651 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.6358. Min Act: -0.1700

Data Index: 422952 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5889. Min Act: -0.1700

Data Index: 1279875 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.6202. Min Act: -0.1700

Data Index: 936103 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5889. Min Act: -0.1700

Data Index: 846316 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.6358. Min Act: -0.1700

Data Index: 66334 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5732. Min Act: -0.1700

Data Index: 624788 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5732. Min Act: -0.1700

Data Index: 61168 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5576. Min Act: -0.1700

Data Index: 319332 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.6202. Min Act: -0.1700

Data Index: 556336 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5889. Min Act: -0.1700

Data Index: 1124670 (C4 (Web Text))

Max Activating Token Index: 922