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

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

Neuron 727 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8986. Min Act: -0.1700

Data Index: 476896 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8986. Min Act: -0.1699

Data Index: 210573 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8673. Min Act: -0.1700

Data Index: 152676 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8673. Min Act: -0.1700

Data Index: 971372 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8360. Min Act: -0.1700

Data Index: 19350 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8360. Min Act: -0.1700

Data Index: 957866 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8360. Min Act: -0.1700

Data Index: 624914 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8360. Min Act: -0.1700

Data Index: 884187 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8360. Min Act: -0.1700

Data Index: 452288 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8047. Min Act: -0.1700

Data Index: 1234125 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8047. Min Act: -0.1700

Data Index: 710035 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8047. Min Act: -0.1700

Data Index: 690698 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7735. Min Act: -0.1700

Data Index: 1060017 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8047. Min Act: -0.1700

Data Index: 811932 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8047. Min Act: -0.1700

Data Index: 1014179 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8047. Min Act: -0.1700

Data Index: 49339 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7735. Min Act: -0.1700

Data Index: 702177 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7735. Min Act: -0.1700

Data Index: 36690 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7735. Min Act: -0.1700

Data Index: 465684 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7735. Min Act: -0.1700

Data Index: 76022 (C4 (Web Text))

Max Activating Token Index: 814