Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 860 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.5189. Min Act: -0.1700

Data Index: 538067 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.4611. Min Act: -0.1700

Data Index: 1361158 (Python Code)

Max Activating Token Index: 117

Text #2

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.3440. Min Act: -0.1700

Data Index: 382652 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.3006. Min Act: -0.1700

Data Index: 379224 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.3072. Min Act: -0.1700

Data Index: 786397 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.2707. Min Act: -0.1700

Data Index: 539342 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.2678. Min Act: -0.1700

Data Index: 1520715 (Python Code)

Max Activating Token Index: 124

Text #7

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.2516. Min Act: -0.1700

Data Index: 386710 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.2659. Min Act: -0.1700

Data Index: 900655 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.2878. Min Act: -0.1700

Data Index: 863776 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.2207. Min Act: -0.1700

Data Index: 1029357 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.2333. Min Act: -0.1699

Data Index: 173811 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.1895. Min Act: -0.1700

Data Index: 1033797 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.1835. Min Act: -0.1700

Data Index: 579409 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.1990. Min Act: -0.1700

Data Index: 195375 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.2007. Min Act: -0.1700

Data Index: 978530 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.2218. Min Act: -0.1700

Data Index: 570214 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.1800. Min Act: -0.1700

Data Index: 617218 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.2064. Min Act: -0.1700

Data Index: 339422 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 6.5189. Min Range: -6.5189

Max Act: 6.1627. Min Act: -0.1700

Data Index: 479220 (C4 (Web Text))

Max Activating Token Index: 49