Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1475 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.3078. Min Act: -0.1700

Data Index: 528629 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2607. Min Act: -0.1700

Data Index: 659278 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2135. Min Act: -0.1700

Data Index: 4279 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.1663. Min Act: -0.1700

Data Index: 976304 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.1663. Min Act: -0.1700

Data Index: 715578 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.1505. Min Act: -0.1700

Data Index: 1273848 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.1348. Min Act: -0.1700

Data Index: 1175960 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.1190. Min Act: -0.1700

Data Index: 937692 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.1033. Min Act: -0.1700

Data Index: 679696 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.1190. Min Act: -0.1700

Data Index: 1344079 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.1033. Min Act: -0.1700

Data Index: 245547 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.1033. Min Act: -0.1700

Data Index: 659663 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.1033. Min Act: -0.1700

Data Index: 482430 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.0875. Min Act: -0.1700

Data Index: 925903 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.0717. Min Act: -0.1700

Data Index: 860064 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.0875. Min Act: -0.1700

Data Index: 806983 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.0875. Min Act: -0.1700

Data Index: 398501 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.0875. Min Act: -0.1700

Data Index: 1208640 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.0875. Min Act: -0.1700

Data Index: 172095 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.0717. Min Act: -0.1700

Data Index: 1008936 (C4 (Web Text))

Max Activating Token Index: 67