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

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

Neuron 157 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.2256. Min Act: -0.1700

Data Index: 835716 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.1784. Min Act: -0.1700

Data Index: 952336 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.1784. Min Act: -0.1700

Data Index: 1057080 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.1941. Min Act: -0.1700

Data Index: 584240 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.1941. Min Act: -0.1700

Data Index: 382480 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.1627. Min Act: -0.1700

Data Index: 225479 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.1627. Min Act: -0.1700

Data Index: 535216 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.1627. Min Act: -0.1700

Data Index: 1266230 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.1627. Min Act: -0.1700

Data Index: 655911 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.1312. Min Act: -0.1700

Data Index: 8495 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.1312. Min Act: -0.1700

Data Index: 777314 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.1154. Min Act: -0.1700

Data Index: 1459321 (Python Code)

Max Activating Token Index: 64

Text #12

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.0996. Min Act: -0.1700

Data Index: 902376 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.1154. Min Act: -0.1700

Data Index: 422614 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.0996. Min Act: -0.1700

Data Index: 1102651 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.0996. Min Act: -0.1700

Data Index: 333197 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.0996. Min Act: -0.1700

Data Index: 274660 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.1154. Min Act: -0.1700

Data Index: 185714 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.0681. Min Act: -0.1700

Data Index: 1181518 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 3.2256. Min Range: -3.2256

Max Act: 3.0523. Min Act: -0.1700

Data Index: 307121 (C4 (Web Text))

Max Activating Token Index: 998