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

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

Neuron 202 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.7884. Min Act: -0.1700

Data Index: 1271132 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.7884. Min Act: -0.1700

Data Index: 437162 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.7259. Min Act: -0.1700

Data Index: 230016 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.5384. Min Act: -0.1700

Data Index: 1085170 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.5697. Min Act: -0.1700

Data Index: 1144974 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.5072. Min Act: -0.1700

Data Index: 536084 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.5697. Min Act: -0.1700

Data Index: 850205 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.5072. Min Act: -0.1700

Data Index: 583058 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.4134. Min Act: -0.1700

Data Index: 733217 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.4134. Min Act: -0.1700

Data Index: 698139 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.3509. Min Act: -0.1700

Data Index: 1336110 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.3822. Min Act: -0.1700

Data Index: 252432 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.3509. Min Act: -0.1700

Data Index: 746947 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.3509. Min Act: -0.1700

Data Index: 1294130 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.4134. Min Act: -0.1700

Data Index: 1212826 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.3509. Min Act: -0.1700

Data Index: 1300382 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.2884. Min Act: -0.1700

Data Index: 707177 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.3197. Min Act: -0.1700

Data Index: 195111 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.3509. Min Act: -0.1700

Data Index: 282496 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 5.7884. Min Range: -5.7884

Max Act: 5.3509. Min Act: -0.1700

Data Index: 967071 (C4 (Web Text))

Max Activating Token Index: 243