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

Dataset: Open Web Text

Neuron 1658 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: 3.3425. Min Range: -3.3425

Max Act: 3.3425. Min Act: -0.1700

Data Index: 8104911 (Open Web Text)

Max Activating Token Index: 33

Text #1

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.3047. Min Act: -0.1700

Data Index: 4910419 (Open Web Text)

Max Activating Token Index: 608

Text #2

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.2492. Min Act: -0.1700

Data Index: 1828335 (Open Web Text)

Max Activating Token Index: 115

Text #3

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.2329. Min Act: -0.1700

Data Index: 3997879 (Open Web Text)

Max Activating Token Index: 208

Text #4

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.1850. Min Act: -0.1700

Data Index: 4272467 (Open Web Text)

Max Activating Token Index: 158

Text #5

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.1985. Min Act: -0.1700

Data Index: 6209483 (Open Web Text)

Max Activating Token Index: 214

Text #6

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.1494. Min Act: -0.1700

Data Index: 6742704 (Open Web Text)

Max Activating Token Index: 917

Text #7

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.1693. Min Act: -0.1700

Data Index: 2754241 (Open Web Text)

Max Activating Token Index: 810

Text #8

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.1525. Min Act: -0.1700

Data Index: 2325427 (Open Web Text)

Max Activating Token Index: 791

Text #9

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.1448. Min Act: -0.1700

Data Index: 6208955 (Open Web Text)

Max Activating Token Index: 445

Text #10

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.1594. Min Act: -0.1700

Data Index: 1616095 (Open Web Text)

Max Activating Token Index: 393

Text #11

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.1428. Min Act: -0.1700

Data Index: 4812818 (Open Web Text)

Max Activating Token Index: 299

Text #12

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.1378. Min Act: -0.1700

Data Index: 1039679 (Open Web Text)

Max Activating Token Index: 688

Text #13

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.1786. Min Act: -0.1700

Data Index: 6357056 (Open Web Text)

Max Activating Token Index: 310

Text #14

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.1677. Min Act: -0.1700

Data Index: 1566446 (Open Web Text)

Max Activating Token Index: 553

Text #15

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.0946. Min Act: -0.1700

Data Index: 6326156 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.1238. Min Act: -0.1700

Data Index: 8422084 (Open Web Text)

Max Activating Token Index: 749

Text #17

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.1242. Min Act: -0.1700

Data Index: 1890883 (Open Web Text)

Max Activating Token Index: 555

Text #18

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.1517. Min Act: -0.1700

Data Index: 6972430 (Open Web Text)

Max Activating Token Index: 613

Text #19

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.1322. Min Act: -0.1700

Data Index: 1681003 (Open Web Text)

Max Activating Token Index: 148