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

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

Neuron 1912 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.7796. Min Act: -0.1700

Data Index: 510006 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.6857. Min Act: -0.1700

Data Index: 691524 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.6544. Min Act: -0.1700

Data Index: 447255 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.6387. Min Act: -0.1700

Data Index: 1172681 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.6544. Min Act: -0.1700

Data Index: 1062368 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.6544. Min Act: -0.1700

Data Index: 757190 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.6387. Min Act: -0.1700

Data Index: 574430 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.6387. Min Act: -0.1700

Data Index: 810021 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.6544. Min Act: -0.1700

Data Index: 70268 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.6074. Min Act: -0.1700

Data Index: 1098842 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.6074. Min Act: -0.1700

Data Index: 1312146 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.6074. Min Act: -0.1700

Data Index: 863650 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.6074. Min Act: -0.1700

Data Index: 959399 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.6074. Min Act: -0.1700

Data Index: 960215 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.6231. Min Act: -0.1700

Data Index: 366264 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.5761. Min Act: -0.1700

Data Index: 715050 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.5918. Min Act: -0.1700

Data Index: 372002 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.5918. Min Act: -0.1700

Data Index: 118845 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.5918. Min Act: -0.1700

Data Index: 542960 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.5918. Min Act: -0.1700

Data Index: 562716 (C4 (Web Text))

Max Activating Token Index: 261