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

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

Neuron 1929 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: 5.4267. Min Range: -5.4267

Max Act: 5.4267. Min Act: -0.1700

Data Index: 168203 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 5.4267. Min Range: -5.4267

Max Act: 5.3017. Min Act: -0.1700

Data Index: 752385 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 5.4267. Min Range: -5.4267

Max Act: 5.1142. Min Act: -0.1700

Data Index: 834364 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 5.4267. Min Range: -5.4267

Max Act: 5.0830. Min Act: -0.1700

Data Index: 1092962 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 5.4267. Min Range: -5.4267

Max Act: 5.0205. Min Act: -0.1700

Data Index: 641596 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 5.4267. Min Range: -5.4267

Max Act: 4.9892. Min Act: -0.1700

Data Index: 1135608 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 5.4267. Min Range: -5.4267

Max Act: 4.9580. Min Act: -0.1700

Data Index: 817538 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 5.4267. Min Range: -5.4267

Max Act: 4.9580. Min Act: -0.1700

Data Index: 1060431 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 5.4267. Min Range: -5.4267

Max Act: 4.8955. Min Act: -0.1700

Data Index: 433378 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 5.4267. Min Range: -5.4267

Max Act: 4.8955. Min Act: -0.1700

Data Index: 720403 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 5.4267. Min Range: -5.4267

Max Act: 4.9267. Min Act: -0.1700

Data Index: 580541 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 5.4267. Min Range: -5.4267

Max Act: 4.9267. Min Act: -0.1700

Data Index: 1237293 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 5.4267. Min Range: -5.4267

Max Act: 4.8955. Min Act: -0.1700

Data Index: 253299 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 5.4267. Min Range: -5.4267

Max Act: 4.8173. Min Act: -0.1700

Data Index: 1199404 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 5.4267. Min Range: -5.4267

Max Act: 4.8955. Min Act: -0.1700

Data Index: 463625 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 5.4267. Min Range: -5.4267

Max Act: 4.8330. Min Act: -0.1700

Data Index: 164990 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 5.4267. Min Range: -5.4267

Max Act: 4.8017. Min Act: -0.1700

Data Index: 561968 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 5.4267. Min Range: -5.4267

Max Act: 4.8330. Min Act: -0.1700

Data Index: 698369 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 5.4267. Min Range: -5.4267

Max Act: 4.8330. Min Act: -0.1700

Data Index: 1028608 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 5.4267. Min Range: -5.4267

Max Act: 4.8173. Min Act: -0.1700

Data Index: 51968 (C4 (Web Text))

Max Activating Token Index: 154