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

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

Neuron 1093 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: 10.9028. Min Range: -10.9028

Max Act: 10.9028. Min Act: -0.1700

Data Index: 1630695 (Python Code)

Max Activating Token Index: 484

Text #1

Max Range: 10.9028. Min Range: -10.9028

Max Act: 10.3602. Min Act: -0.1700

Data Index: 1579452 (Python Code)

Max Activating Token Index: 130

Text #2

Max Range: 10.9028. Min Range: -10.9028

Max Act: 10.2909. Min Act: -0.1700

Data Index: 564233 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 10.9028. Min Range: -10.9028

Max Act: 10.3498. Min Act: -0.1700

Data Index: 708571 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 10.9028. Min Range: -10.9028

Max Act: 10.1812. Min Act: -0.1700

Data Index: 463915 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 10.9028. Min Range: -10.9028

Max Act: 10.0718. Min Act: -0.1700

Data Index: 70595 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 10.9028. Min Range: -10.9028

Max Act: 9.9610. Min Act: -0.1700

Data Index: 174821 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 10.9028. Min Range: -10.9028

Max Act: 9.9477. Min Act: -0.1700

Data Index: 1437666 (Python Code)

Max Activating Token Index: 391

Text #8

Max Range: 10.9028. Min Range: -10.9028

Max Act: 9.7551. Min Act: -0.1700

Data Index: 285799 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 10.9028. Min Range: -10.9028

Max Act: 9.7948. Min Act: -0.1700

Data Index: 5479 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 10.9028. Min Range: -10.9028

Max Act: 9.7831. Min Act: -0.1700

Data Index: 1012919 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 10.9028. Min Range: -10.9028

Max Act: 9.7398. Min Act: -0.1700

Data Index: 1030977 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 10.9028. Min Range: -10.9028

Max Act: 9.7533. Min Act: -0.1700

Data Index: 77843 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 10.9028. Min Range: -10.9028

Max Act: 9.7206. Min Act: -0.1700

Data Index: 672646 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 10.9028. Min Range: -10.9028

Max Act: 9.7426. Min Act: -0.1700

Data Index: 983176 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 10.9028. Min Range: -10.9028

Max Act: 9.7181. Min Act: -0.1700

Data Index: 1219819 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 10.9028. Min Range: -10.9028

Max Act: 9.7528. Min Act: -0.1700

Data Index: 1265668 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 10.9028. Min Range: -10.9028

Max Act: 9.6696. Min Act: -0.1700

Data Index: 762184 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 10.9028. Min Range: -10.9028

Max Act: 9.6345. Min Act: -0.1700

Data Index: 1048597 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 10.9028. Min Range: -10.9028

Max Act: 9.5295. Min Act: -0.1700

Data Index: 552423 (C4 (Web Text))

Max Activating Token Index: 732