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

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

Neuron 1794 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: 5.7972. Min Range: -5.7972

Max Act: 5.7972. Min Act: -0.1700

Data Index: 955238 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.6722. Min Act: -0.1700

Data Index: 703179 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.6722. Min Act: -0.1700

Data Index: 623624 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.6097. Min Act: -0.1696

Data Index: 1210293 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.5160. Min Act: -0.1700

Data Index: 1309065 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.4535. Min Act: -0.1700

Data Index: 67869 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.3597. Min Act: -0.1700

Data Index: 586537 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.3285. Min Act: -0.1700

Data Index: 678599 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.2972. Min Act: -0.1700

Data Index: 245606 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.3285. Min Act: -0.1700

Data Index: 1323352 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.3285. Min Act: -0.1700

Data Index: 1247235 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.2972. Min Act: -0.1700

Data Index: 797567 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.2347. Min Act: -0.1700

Data Index: 791593 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.2660. Min Act: -0.1700

Data Index: 686026 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.2035. Min Act: -0.1700

Data Index: 222490 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.1722. Min Act: -0.1700

Data Index: 825273 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.1722. Min Act: -0.1699

Data Index: 500661 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.1722. Min Act: -0.1700

Data Index: 118545 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.1410. Min Act: -0.1700

Data Index: 684705 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 5.7972. Min Range: -5.7972

Max Act: 5.1410. Min Act: -0.1700

Data Index: 717017 (C4 (Web Text))

Max Activating Token Index: 958