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

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

Neuron 1424 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: 5.6085. Min Range: -5.6085

Max Act: 5.6085. Min Act: -0.1700

Data Index: 1075054 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.6085. Min Act: -0.1700

Data Index: 922593 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.5460. Min Act: -0.1700

Data Index: 892834 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.6085. Min Act: -0.1700

Data Index: 823307 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.5773. Min Act: -0.1700

Data Index: 256800 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.5460. Min Act: -0.1700

Data Index: 351169 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.4835. Min Act: -0.1700

Data Index: 43068 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.5148. Min Act: -0.1700

Data Index: 1079126 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.4523. Min Act: -0.1700

Data Index: 848407 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.4835. Min Act: -0.1700

Data Index: 1010588 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.4210. Min Act: -0.1700

Data Index: 363567 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.4523. Min Act: -0.1700

Data Index: 1068355 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.3585. Min Act: -0.1700

Data Index: 174258 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.3585. Min Act: -0.1700

Data Index: 1254150 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.3585. Min Act: -0.1700

Data Index: 755905 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.3585. Min Act: -0.1700

Data Index: 519400 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.3273. Min Act: -0.1700

Data Index: 686039 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.3273. Min Act: -0.1700

Data Index: 502151 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.3273. Min Act: -0.1700

Data Index: 353192 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 5.6085. Min Range: -5.6085

Max Act: 5.2960. Min Act: -0.1700

Data Index: 574768 (C4 (Web Text))

Max Activating Token Index: 920