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

Dataset: Open Web Text

Neuron 1283 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: 4.5242. Min Range: -4.5242

Max Act: 4.4527. Min Act: -0.1700

Data Index: 5063126 (Open Web Text)

Max Activating Token Index: 650

Text #1

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.4707. Min Act: -0.1700

Data Index: 3480971 (Open Web Text)

Max Activating Token Index: 699

Text #2

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.4670. Min Act: -0.1700

Data Index: 1165171 (Open Web Text)

Max Activating Token Index: 262

Text #3

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.5242. Min Act: -0.1700

Data Index: 2950501 (Open Web Text)

Max Activating Token Index: 990

Text #4

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.4369. Min Act: -0.1700

Data Index: 7578659 (Open Web Text)

Max Activating Token Index: 137

Text #5

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.3964. Min Act: -0.1700

Data Index: 1006995 (Open Web Text)

Max Activating Token Index: 299

Text #6

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.3014. Min Act: -0.1700

Data Index: 5956162 (Open Web Text)

Max Activating Token Index: 393

Text #7

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.3444. Min Act: -0.1700

Data Index: 2982319 (Open Web Text)

Max Activating Token Index: 599

Text #8

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.3455. Min Act: -0.1700

Data Index: 5702052 (Open Web Text)

Max Activating Token Index: 808

Text #9

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.3661. Min Act: -0.1700

Data Index: 1240409 (Open Web Text)

Max Activating Token Index: 655

Text #10

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.2611. Min Act: -0.1700

Data Index: 4991422 (Open Web Text)

Max Activating Token Index: 801

Text #11

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.2771. Min Act: -0.1700

Data Index: 3323160 (Open Web Text)

Max Activating Token Index: 565

Text #12

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.2747. Min Act: -0.1700

Data Index: 220960 (Open Web Text)

Max Activating Token Index: 511

Text #13

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.3167. Min Act: -0.1700

Data Index: 452185 (Open Web Text)

Max Activating Token Index: 296

Text #14

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.2800. Min Act: -0.1700

Data Index: 5956163 (Open Web Text)

Max Activating Token Index: 617

Text #15

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.2604. Min Act: -0.1700

Data Index: 4294090 (Open Web Text)

Max Activating Token Index: 872

Text #16

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.2871. Min Act: -0.1700

Data Index: 537617 (Open Web Text)

Max Activating Token Index: 709

Text #17

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.2544. Min Act: -0.1700

Data Index: 3406702 (Open Web Text)

Max Activating Token Index: 168

Text #18

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.2879. Min Act: -0.1700

Data Index: 242270 (Open Web Text)

Max Activating Token Index: 922

Text #19

Max Range: 4.5242. Min Range: -4.5242

Max Act: 4.2871. Min Act: -0.1700

Data Index: 1046826 (Open Web Text)

Max Activating Token Index: 382