Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 221 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.7480. Min Act: -0.1700

Data Index: 1524755 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.6479. Min Act: -0.1700

Data Index: 4463950 (Open Web Text)

Max Activating Token Index: 529

Text #2

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.6235. Min Act: -0.1700

Data Index: 446017 (Open Web Text)

Max Activating Token Index: 143

Text #3

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.6158. Min Act: -0.1700

Data Index: 7919725 (Open Web Text)

Max Activating Token Index: 399

Text #4

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.6028. Min Act: -0.1700

Data Index: 2451277 (Open Web Text)

Max Activating Token Index: 710

Text #5

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.6043. Min Act: -0.1700

Data Index: 7575916 (Open Web Text)

Max Activating Token Index: 83

Text #6

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5953. Min Act: -0.1700

Data Index: 351415 (Open Web Text)

Max Activating Token Index: 135

Text #7

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5947. Min Act: -0.1699

Data Index: 7434791 (Open Web Text)

Max Activating Token Index: 682

Text #8

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5910. Min Act: -0.1700

Data Index: 4537455 (Open Web Text)

Max Activating Token Index: 343

Text #9

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5877. Min Act: -0.1700

Data Index: 1524752 (Open Web Text)

Max Activating Token Index: 678

Text #10

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5814. Min Act: -0.1700

Data Index: 2653007 (Open Web Text)

Max Activating Token Index: 251

Text #11

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5827. Min Act: -0.1700

Data Index: 2518630 (Open Web Text)

Max Activating Token Index: 418

Text #12

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5810. Min Act: -0.1700

Data Index: 6895347 (Open Web Text)

Max Activating Token Index: 621

Text #13

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5795. Min Act: -0.1700

Data Index: 5331033 (Open Web Text)

Max Activating Token Index: 371

Text #14

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5791. Min Act: -0.1700

Data Index: 2655909 (Open Web Text)

Max Activating Token Index: 245

Text #15

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5795. Min Act: -0.1700

Data Index: 1524753 (Open Web Text)

Max Activating Token Index: 166

Text #16

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5739. Min Act: -0.1700

Data Index: 369950 (Open Web Text)

Max Activating Token Index: 694

Text #17

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5698. Min Act: -0.1698

Data Index: 1145179 (Open Web Text)

Max Activating Token Index: 750

Text #18

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5668. Min Act: -0.1700

Data Index: 2026114 (Open Web Text)

Max Activating Token Index: 434

Text #19

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5628. Min Act: -0.1700

Data Index: 5804350 (Open Web Text)

Max Activating Token Index: 638