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

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

Neuron 1544 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: 5.3061. Min Range: -5.3061

Max Act: 5.3061. Min Act: -0.1700

Data Index: 137865 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.3061. Min Act: -0.1700

Data Index: 921615 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.3061. Min Act: -0.1700

Data Index: 1345346 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.3061. Min Act: -0.1700

Data Index: 10502 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.2436. Min Act: -0.1700

Data Index: 1167658 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.2123. Min Act: -0.1700

Data Index: 920766 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.2436. Min Act: -0.1700

Data Index: 932736 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.2123. Min Act: -0.1700

Data Index: 990217 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.1811. Min Act: -0.1700

Data Index: 1340671 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.1186. Min Act: -0.1700

Data Index: 1358870 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.1186. Min Act: -0.1700

Data Index: 200586 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.1186. Min Act: -0.1700

Data Index: 673256 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.1186. Min Act: -0.1700

Data Index: 466094 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.1498. Min Act: -0.1700

Data Index: 390990 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.1186. Min Act: -0.1700

Data Index: 448525 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.1186. Min Act: -0.1700

Data Index: 789821 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.1186. Min Act: -0.1700

Data Index: 1003314 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.1186. Min Act: -0.1700

Data Index: 94989 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.1186. Min Act: -0.1700

Data Index: 1089313 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 5.3061. Min Range: -5.3061

Max Act: 5.1186. Min Act: -0.1700

Data Index: 355618 (C4 (Web Text))

Max Activating Token Index: 151