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

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

Neuron 110 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.8645. Min Act: -0.1700

Data Index: 1334515 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.7081. Min Act: -0.1700

Data Index: 845268 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.7081. Min Act: -0.1700

Data Index: 212104 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.7237. Min Act: -0.1700

Data Index: 1112831 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.7237. Min Act: -0.1700

Data Index: 810534 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.7237. Min Act: -0.1700

Data Index: 402320 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.6298. Min Act: -0.1700

Data Index: 283692 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.5829. Min Act: -0.1700

Data Index: 1255917 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.5829. Min Act: -0.1700

Data Index: 663667 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.5672. Min Act: -0.1700

Data Index: 865431 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.5985. Min Act: -0.1700

Data Index: 55323 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.5672. Min Act: -0.1700

Data Index: 687699 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.5515. Min Act: -0.1700

Data Index: 360403 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.5985. Min Act: -0.1700

Data Index: 328877 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.5985. Min Act: -0.1700

Data Index: 950900 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.5359. Min Act: -0.1700

Data Index: 263538 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.5672. Min Act: -0.1700

Data Index: 6837 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.5515. Min Act: -0.1700

Data Index: 538932 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.5359. Min Act: -0.1700

Data Index: 1038162 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 3.8645. Min Range: -3.8645

Max Act: 3.5672. Min Act: -0.1700

Data Index: 1089183 (C4 (Web Text))

Max Activating Token Index: 8