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

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

Neuron 1511 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: 2.8308. Min Range: -2.8308

Max Act: 2.8308. Min Act: -0.1700

Data Index: 900478 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.8069. Min Act: -0.1700

Data Index: 516307 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.8198. Min Act: -0.1700

Data Index: 883970 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.7705. Min Act: -0.1699

Data Index: 554813 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.7258. Min Act: -0.1699

Data Index: 16299 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.7213. Min Act: -0.1700

Data Index: 56664 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.6696. Min Act: -0.1700

Data Index: 1424233 (Python Code)

Max Activating Token Index: 800

Text #7

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.6731. Min Act: -0.1697

Data Index: 483375 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.6318. Min Act: -0.1700

Data Index: 958108 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.6085. Min Act: -0.1700

Data Index: 708797 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.6235. Min Act: -0.1700

Data Index: 1612538 (Python Code)

Max Activating Token Index: 746

Text #11

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.6175. Min Act: -0.1700

Data Index: 1541169 (Python Code)

Max Activating Token Index: 673

Text #12

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.5809. Min Act: -0.1700

Data Index: 1515681 (Python Code)

Max Activating Token Index: 499

Text #13

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.5835. Min Act: -0.1700

Data Index: 1151113 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.5641. Min Act: -0.1700

Data Index: 948832 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.5940. Min Act: -0.1699

Data Index: 990989 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.5570. Min Act: -0.1700

Data Index: 426626 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.5362. Min Act: -0.1700

Data Index: 802970 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.5401. Min Act: -0.1699

Data Index: 278507 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 2.8308. Min Range: -2.8308

Max Act: 2.5422. Min Act: -0.1700

Data Index: 442638 (C4 (Web Text))

Max Activating Token Index: 387