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

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

Neuron 367 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: 8.2740. Min Range: -8.2740

Max Act: 8.2740. Min Act: -0.1700

Data Index: 654590 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 8.2740. Min Range: -8.2740

Max Act: 8.1802. Min Act: -0.1700

Data Index: 202039 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 8.2740. Min Range: -8.2740

Max Act: 8.0240. Min Act: -0.1700

Data Index: 1317239 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.9615. Min Act: -0.1700

Data Index: 506420 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.9302. Min Act: -0.1700

Data Index: 1087551 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.8990. Min Act: -0.1700

Data Index: 259225 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.8365. Min Act: -0.1700

Data Index: 536127 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.8990. Min Act: -0.1700

Data Index: 77012 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.8990. Min Act: -0.1699

Data Index: 611386 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.8990. Min Act: -0.1700

Data Index: 15385 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.8677. Min Act: -0.1700

Data Index: 1308047 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.9302. Min Act: -0.1700

Data Index: 773393 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.8677. Min Act: -0.1700

Data Index: 20255 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.8677. Min Act: -0.1700

Data Index: 1277085 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.8365. Min Act: -0.1700

Data Index: 425056 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.8052. Min Act: -0.1700

Data Index: 734571 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.8365. Min Act: -0.1700

Data Index: 1207448 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.8365. Min Act: -0.1700

Data Index: 1272446 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.8365. Min Act: -0.1700

Data Index: 717883 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 8.2740. Min Range: -8.2740

Max Act: 7.8365. Min Act: -0.1700

Data Index: 330588 (C4 (Web Text))

Max Activating Token Index: 384