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

Dataset: Open Web Text

Neuron 1888 in Layer 3

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: 3.8242. Min Range: -3.8242

Max Act: 3.8242. Min Act: -0.1700

Data Index: 5959328 (Open Web Text)

Max Activating Token Index: 977

Text #1

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7651. Min Act: -0.1700

Data Index: 3994011 (Open Web Text)

Max Activating Token Index: 624

Text #2

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7509. Min Act: -0.1700

Data Index: 209172 (Open Web Text)

Max Activating Token Index: 645

Text #3

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7189. Min Act: -0.1700

Data Index: 3082638 (Open Web Text)

Max Activating Token Index: 701

Text #4

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7161. Min Act: -0.1700

Data Index: 3424727 (Open Web Text)

Max Activating Token Index: 539

Text #5

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6750. Min Act: -0.1700

Data Index: 8582311 (Open Web Text)

Max Activating Token Index: 452

Text #6

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6475. Min Act: -0.1700

Data Index: 1281327 (Open Web Text)

Max Activating Token Index: 719

Text #7

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6396. Min Act: -0.1698

Data Index: 380276 (Open Web Text)

Max Activating Token Index: 773

Text #8

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6001. Min Act: -0.1700

Data Index: 451277 (Open Web Text)

Max Activating Token Index: 699

Text #9

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6394. Min Act: -0.1700

Data Index: 993362 (Open Web Text)

Max Activating Token Index: 830

Text #10

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6066. Min Act: -0.1700

Data Index: 358730 (Open Web Text)

Max Activating Token Index: 380

Text #11

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.5654. Min Act: -0.1700

Data Index: 1694323 (Open Web Text)

Max Activating Token Index: 689

Text #12

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.5933. Min Act: -0.1700

Data Index: 2321533 (Open Web Text)

Max Activating Token Index: 963

Text #13

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.5368. Min Act: -0.1700

Data Index: 8494489 (Open Web Text)

Max Activating Token Index: 812

Text #14

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.5313. Min Act: -0.1700

Data Index: 6862455 (Open Web Text)

Max Activating Token Index: 541

Text #15

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.5107. Min Act: -0.1700

Data Index: 6680434 (Open Web Text)

Max Activating Token Index: 542

Text #16

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.5053. Min Act: -0.1700

Data Index: 2114428 (Open Web Text)

Max Activating Token Index: 443

Text #17

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.5294. Min Act: -0.1700

Data Index: 4851540 (Open Web Text)

Max Activating Token Index: 811

Text #18

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.4684. Min Act: -0.1699

Data Index: 7958280 (Open Web Text)

Max Activating Token Index: 844

Text #19

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.4964. Min Act: -0.1700

Data Index: 5396476 (Open Web Text)

Max Activating Token Index: 714