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

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

Neuron 1305 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.3174. Min Act: -0.1700

Data Index: 54950 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.2389. Min Act: -0.1700

Data Index: 1215858 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1917. Min Act: -0.1700

Data Index: 1065620 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.2074. Min Act: -0.1700

Data Index: 456702 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1917. Min Act: -0.1700

Data Index: 687194 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1917. Min Act: -0.1700

Data Index: 1311308 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1760. Min Act: -0.1700

Data Index: 1614218 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1760. Min Act: -0.1700

Data Index: 83096 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1760. Min Act: -0.1700

Data Index: 334773 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1602. Min Act: -0.1700

Data Index: 711241 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1602. Min Act: -0.1700

Data Index: 1461671 (Python Code)

Max Activating Token Index: 457

Text #11

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1602. Min Act: -0.1700

Data Index: 1216090 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1602. Min Act: -0.1700

Data Index: 1219311 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1602. Min Act: -0.1700

Data Index: 427765 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1602. Min Act: -0.1700

Data Index: 709054 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1760. Min Act: -0.1700

Data Index: 230647 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1287. Min Act: -0.1700

Data Index: 742297 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1287. Min Act: -0.1700

Data Index: 872624 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1445. Min Act: -0.1700

Data Index: 996612 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 3.3174. Min Range: -3.3174

Max Act: 3.1287. Min Act: -0.1700

Data Index: 1034604 (C4 (Web Text))

Max Activating Token Index: 42