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

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

Neuron 455 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.3989. Min Act: -0.1700

Data Index: 1063659 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.3047. Min Act: -0.1700

Data Index: 1085731 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.2576. Min Act: -0.1700

Data Index: 657905 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.2419. Min Act: -0.1700

Data Index: 1090246 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.2262. Min Act: -0.1700

Data Index: 544947 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.2262. Min Act: -0.1700

Data Index: 302026 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.2104. Min Act: -0.1700

Data Index: 492024 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1947. Min Act: -0.1700

Data Index: 1081613 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1790. Min Act: -0.1700

Data Index: 1048011 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1790. Min Act: -0.1700

Data Index: 144430 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1790. Min Act: -0.1700

Data Index: 1165447 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1632. Min Act: -0.1700

Data Index: 583217 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1475. Min Act: -0.1700

Data Index: 1254082 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1790. Min Act: -0.1700

Data Index: 350679 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1475. Min Act: -0.1700

Data Index: 301478 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1475. Min Act: -0.1700

Data Index: 373912 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1475. Min Act: -0.1700

Data Index: 617439 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1475. Min Act: -0.1700

Data Index: 1156832 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1632. Min Act: -0.1700

Data Index: 283961 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1317. Min Act: -0.1700

Data Index: 872080 (C4 (Web Text))

Max Activating Token Index: 192