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

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

Neuron 683 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: 5.2516. Min Range: -5.2516

Max Act: 5.2516. Min Act: -0.1700

Data Index: 1133266 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.9391. Min Act: -0.1700

Data Index: 133067 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.9704. Min Act: -0.1700

Data Index: 1190017 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.8766. Min Act: -0.1700

Data Index: 629072 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.9079. Min Act: -0.1700

Data Index: 470480 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.9391. Min Act: -0.1700

Data Index: 297026 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.8766. Min Act: -0.1700

Data Index: 958395 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.9079. Min Act: -0.1700

Data Index: 163335 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.9079. Min Act: -0.1700

Data Index: 591845 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.8766. Min Act: -0.1700

Data Index: 127379 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.8454. Min Act: -0.1700

Data Index: 1028171 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.8454. Min Act: -0.1700

Data Index: 32732 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.8141. Min Act: -0.1700

Data Index: 1096290 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.8141. Min Act: -0.1700

Data Index: 67073 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.8454. Min Act: -0.1700

Data Index: 252346 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.8141. Min Act: -0.1700

Data Index: 705003 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.8454. Min Act: -0.1700

Data Index: 1158972 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.8454. Min Act: -0.1700

Data Index: 243166 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.8141. Min Act: -0.1700

Data Index: 365734 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.8454. Min Act: -0.1700

Data Index: 1031227 (C4 (Web Text))

Max Activating Token Index: 950