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

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

Neuron 1465 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: 3.8332. Min Range: -3.8332

Max Act: 3.8332. Min Act: -0.1700

Data Index: 1468192 (Python Code)

Max Activating Token Index: 582

Text #1

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.8019. Min Act: -0.1700

Data Index: 185427 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.7393. Min Act: -0.1700

Data Index: 120398 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.7080. Min Act: -0.1700

Data Index: 1113121 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.6454. Min Act: -0.1700

Data Index: 211180 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.6767. Min Act: -0.1700

Data Index: 184671 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.6454. Min Act: -0.1700

Data Index: 1328884 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.6454. Min Act: -0.1700

Data Index: 1084518 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.6141. Min Act: -0.1700

Data Index: 1285173 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.6141. Min Act: -0.1700

Data Index: 615252 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.5828. Min Act: -0.1700

Data Index: 90495 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.5828. Min Act: -0.1700

Data Index: 261427 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.5828. Min Act: -0.1700

Data Index: 876975 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.5828. Min Act: -0.1700

Data Index: 597455 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.5201. Min Act: -0.1700

Data Index: 555112 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.5201. Min Act: -0.1700

Data Index: 918915 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.5201. Min Act: -0.1700

Data Index: 1063572 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.5515. Min Act: -0.1700

Data Index: 935439 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.5515. Min Act: -0.1700

Data Index: 662194 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 3.8332. Min Range: -3.8332

Max Act: 3.5201. Min Act: -0.1700

Data Index: 238191 (C4 (Web Text))

Max Activating Token Index: 588