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

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

Neuron 1714 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.1926. Min Act: -0.1700

Data Index: 1081109 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.1769. Min Act: -0.1700

Data Index: 834042 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.1454. Min Act: -0.1700

Data Index: 446958 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.1296. Min Act: -0.1700

Data Index: 877053 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0981. Min Act: -0.1700

Data Index: 290013 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0981. Min Act: -0.1700

Data Index: 1098227 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0666. Min Act: -0.1700

Data Index: 382871 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0508. Min Act: -0.1700

Data Index: 362044 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0666. Min Act: -0.1700

Data Index: 319680 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0508. Min Act: -0.1700

Data Index: 747174 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0350. Min Act: -0.1700

Data Index: 612387 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0508. Min Act: -0.1700

Data Index: 1168859 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0508. Min Act: -0.1700

Data Index: 1334280 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0508. Min Act: -0.1700

Data Index: 545357 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0350. Min Act: -0.1700

Data Index: 128681 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0350. Min Act: -0.1700

Data Index: 57492 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0350. Min Act: -0.1700

Data Index: 1076215 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0034. Min Act: -0.1700

Data Index: 498349 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0350. Min Act: -0.1700

Data Index: 382910 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 3.1926. Min Range: -3.1926

Max Act: 3.0192. Min Act: -0.1700

Data Index: 753088 (C4 (Web Text))

Max Activating Token Index: 84