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

Dataset: Open Web Text

Neuron 2546 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: 4.3342. Min Range: -4.3342

Max Act: 4.2396. Min Act: -0.1700

Data Index: 7135482 (Open Web Text)

Max Activating Token Index: 601

Text #1

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.2298. Min Act: -0.1700

Data Index: 5116864 (Open Web Text)

Max Activating Token Index: 766

Text #2

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.3342. Min Act: -0.1700

Data Index: 4263286 (Open Web Text)

Max Activating Token Index: 349

Text #3

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.2329. Min Act: -0.1700

Data Index: 7430716 (Open Web Text)

Max Activating Token Index: 677

Text #4

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.2642. Min Act: -0.1700

Data Index: 5573274 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.1402. Min Act: -0.1700

Data Index: 7345719 (Open Web Text)

Max Activating Token Index: 620

Text #6

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.2306. Min Act: -0.1700

Data Index: 4027045 (Open Web Text)

Max Activating Token Index: 347

Text #7

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.2222. Min Act: -0.1700

Data Index: 1034722 (Open Web Text)

Max Activating Token Index: 618

Text #8

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.1586. Min Act: -0.1700

Data Index: 5149166 (Open Web Text)

Max Activating Token Index: 430

Text #9

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.1858. Min Act: -0.1700

Data Index: 5993651 (Open Web Text)

Max Activating Token Index: 214

Text #10

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.1954. Min Act: -0.1700

Data Index: 8109062 (Open Web Text)

Max Activating Token Index: 639

Text #11

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.2145. Min Act: -0.1700

Data Index: 757086 (Open Web Text)

Max Activating Token Index: 608

Text #12

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.1397. Min Act: -0.1700

Data Index: 705964 (Open Web Text)

Max Activating Token Index: 600

Text #13

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.1501. Min Act: -0.1700

Data Index: 1298465 (Open Web Text)

Max Activating Token Index: 156

Text #14

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.1757. Min Act: -0.1700

Data Index: 2497911 (Open Web Text)

Max Activating Token Index: 116

Text #15

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.2210. Min Act: -0.1700

Data Index: 210433 (Open Web Text)

Max Activating Token Index: 762

Text #16

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.1845. Min Act: -0.1700

Data Index: 642668 (Open Web Text)

Max Activating Token Index: 641

Text #17

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.0890. Min Act: -0.1700

Data Index: 93909 (Open Web Text)

Max Activating Token Index: 537

Text #18

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.1772. Min Act: -0.1700

Data Index: 3302171 (Open Web Text)

Max Activating Token Index: 660

Text #19

Max Range: 4.3342. Min Range: -4.3342

Max Act: 4.1190. Min Act: -0.1700

Data Index: 4341766 (Open Web Text)

Max Activating Token Index: 970