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

Dataset: Open Web Text

Neuron 489 in Layer 5

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: 4.1386. Min Range: -4.1386

Max Act: 4.1386. Min Act: -0.1700

Data Index: 4797042 (Open Web Text)

Max Activating Token Index: 462

Text #1

Max Range: 4.1386. Min Range: -4.1386

Max Act: 4.0374. Min Act: -0.1700

Data Index: 2895095 (Open Web Text)

Max Activating Token Index: 809

Text #2

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.9342. Min Act: -0.1700

Data Index: 6051076 (Open Web Text)

Max Activating Token Index: 757

Text #3

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.8639. Min Act: -0.1700

Data Index: 3778455 (Open Web Text)

Max Activating Token Index: 277

Text #4

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.8579. Min Act: -0.1700

Data Index: 5298185 (Open Web Text)

Max Activating Token Index: 803

Text #5

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.8227. Min Act: -0.1700

Data Index: 1096533 (Open Web Text)

Max Activating Token Index: 678

Text #6

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.7567. Min Act: -0.1700

Data Index: 1776511 (Open Web Text)

Max Activating Token Index: 974

Text #7

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.7958. Min Act: -0.1700

Data Index: 3284747 (Open Web Text)

Max Activating Token Index: 885

Text #8

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.7491. Min Act: -0.1700

Data Index: 5947935 (Open Web Text)

Max Activating Token Index: 903

Text #9

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.7611. Min Act: -0.1700

Data Index: 510454 (Open Web Text)

Max Activating Token Index: 240

Text #10

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.7648. Min Act: -0.1700

Data Index: 2128576 (Open Web Text)

Max Activating Token Index: 363

Text #11

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.7375. Min Act: -0.1700

Data Index: 4967466 (Open Web Text)

Max Activating Token Index: 482

Text #12

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.7295. Min Act: -0.1700

Data Index: 8043194 (Open Web Text)

Max Activating Token Index: 197

Text #13

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.7246. Min Act: -0.1700

Data Index: 6376106 (Open Web Text)

Max Activating Token Index: 468

Text #14

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.7040. Min Act: -0.1700

Data Index: 2860799 (Open Web Text)

Max Activating Token Index: 849

Text #15

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.6766. Min Act: -0.1700

Data Index: 664619 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.7193. Min Act: -0.1700

Data Index: 5298186 (Open Web Text)

Max Activating Token Index: 194

Text #17

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.7182. Min Act: -0.1700

Data Index: 3002020 (Open Web Text)

Max Activating Token Index: 811

Text #18

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.6891. Min Act: -0.1700

Data Index: 8590905 (Open Web Text)

Max Activating Token Index: 381

Text #19

Max Range: 4.1386. Min Range: -4.1386

Max Act: 3.6779. Min Act: -0.1700

Data Index: 5557266 (Open Web Text)

Max Activating Token Index: 270