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

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

Neuron 1087 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.6710. Min Act: -0.1700

Data Index: 474051 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.7335. Min Act: -0.1700

Data Index: 1101479 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.7023. Min Act: -0.1700

Data Index: 843439 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.6085. Min Act: -0.1700

Data Index: 79705 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.5460. Min Act: -0.1700

Data Index: 1000733 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.4835. Min Act: -0.1700

Data Index: 126340 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.4835. Min Act: -0.1700

Data Index: 660831 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.3898. Min Act: -0.1700

Data Index: 992216 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.4523. Min Act: -0.1700

Data Index: 1068521 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.3898. Min Act: -0.1700

Data Index: 451268 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.3585. Min Act: -0.1700

Data Index: 373457 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.3898. Min Act: -0.1700

Data Index: 1273150 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.2648. Min Act: -0.1700

Data Index: 1103708 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.2648. Min Act: -0.1700

Data Index: 1084294 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.3585. Min Act: -0.1700

Data Index: 459281 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.3273. Min Act: -0.1700

Data Index: 1230600 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.2960. Min Act: -0.1700

Data Index: 602879 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.2648. Min Act: -0.1700

Data Index: 643618 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.3273. Min Act: -0.1700

Data Index: 250836 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 5.7335. Min Range: -5.7335

Max Act: 5.2960. Min Act: -0.1700

Data Index: 136255 (C4 (Web Text))

Max Activating Token Index: 145