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

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

Neuron 1421 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: 5.2552. Min Range: -5.2552

Max Act: 5.2552. Min Act: -0.1700

Data Index: 879403 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 5.2552. Min Range: -5.2552

Max Act: 5.0364. Min Act: -0.1700

Data Index: 84092 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9739. Min Act: -0.1700

Data Index: 1251209 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9427. Min Act: -0.1700

Data Index: 494636 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9427. Min Act: -0.1700

Data Index: 506292 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9427. Min Act: -0.1700

Data Index: 788042 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9739. Min Act: -0.1700

Data Index: 1251238 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9427. Min Act: -0.1700

Data Index: 438930 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9427. Min Act: -0.1700

Data Index: 269608 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.8489. Min Act: -0.1700

Data Index: 230300 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 5.2552. Min Range: -5.2552

Max Act: 5.0364. Min Act: -0.1700

Data Index: 252860 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 5.2552. Min Range: -5.2552

Max Act: 5.0364. Min Act: -0.1700

Data Index: 18662 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.8177. Min Act: -0.1700

Data Index: 289619 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9427. Min Act: -0.1700

Data Index: 671539 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9427. Min Act: -0.1700

Data Index: 599242 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9114. Min Act: -0.1700

Data Index: 1304102 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.8802. Min Act: -0.1700

Data Index: 835429 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.9427. Min Act: -0.1700

Data Index: 532766 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.8802. Min Act: -0.1700

Data Index: 328011 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 5.2552. Min Range: -5.2552

Max Act: 4.8802. Min Act: -0.1700

Data Index: 110506 (C4 (Web Text))

Max Activating Token Index: 542