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

Dataset: Open Web Text

Neuron 1410 in Layer 2

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: 3.6096. Min Range: -3.6096

Max Act: 3.6096. Min Act: -0.1700

Data Index: 3756420 (Open Web Text)

Max Activating Token Index: 426

Text #1

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.5653. Min Act: -0.1700

Data Index: 7651323 (Open Web Text)

Max Activating Token Index: 714

Text #2

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.5498. Min Act: -0.1700

Data Index: 5350634 (Open Web Text)

Max Activating Token Index: 171

Text #3

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.3454. Min Act: -0.1700

Data Index: 30705 (Open Web Text)

Max Activating Token Index: 359

Text #4

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.3546. Min Act: -0.1700

Data Index: 7489792 (Open Web Text)

Max Activating Token Index: 46

Text #5

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.3100. Min Act: -0.1700

Data Index: 2974286 (Open Web Text)

Max Activating Token Index: 60

Text #6

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.3191. Min Act: -0.1700

Data Index: 8749927 (Open Web Text)

Max Activating Token Index: 204

Text #7

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.3024. Min Act: -0.1700

Data Index: 6609456 (Open Web Text)

Max Activating Token Index: 712

Text #8

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.2945. Min Act: -0.1700

Data Index: 5892073 (Open Web Text)

Max Activating Token Index: 481

Text #9

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.2835. Min Act: -0.1700

Data Index: 194063 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.2796. Min Act: -0.1700

Data Index: 623411 (Open Web Text)

Max Activating Token Index: 993

Text #11

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.2738. Min Act: -0.1700

Data Index: 273672 (Open Web Text)

Max Activating Token Index: 811

Text #12

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.2593. Min Act: -0.1700

Data Index: 1366094 (Open Web Text)

Max Activating Token Index: 35

Text #13

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.2529. Min Act: -0.1700

Data Index: 5124054 (Open Web Text)

Max Activating Token Index: 648

Text #14

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.2445. Min Act: -0.1700

Data Index: 6208772 (Open Web Text)

Max Activating Token Index: 149

Text #15

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.2349. Min Act: -0.1700

Data Index: 8670428 (Open Web Text)

Max Activating Token Index: 595

Text #16

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.2298. Min Act: -0.1700

Data Index: 7859103 (Open Web Text)

Max Activating Token Index: 288

Text #17

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.2309. Min Act: -0.1700

Data Index: 2813601 (Open Web Text)

Max Activating Token Index: 206

Text #18

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.2150. Min Act: -0.1700

Data Index: 1130491 (Open Web Text)

Max Activating Token Index: 248

Text #19

Max Range: 3.6096. Min Range: -3.6096

Max Act: 3.1933. Min Act: -0.1700

Data Index: 5862026 (Open Web Text)

Max Activating Token Index: 28