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

Dataset: Open Web Text

Neuron 890 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: 5.0286. Min Range: -5.0286

Max Act: 5.0286. Min Act: -0.1700

Data Index: 1004078 (Open Web Text)

Max Activating Token Index: 236

Text #1

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.9843. Min Act: -0.1700

Data Index: 4228398 (Open Web Text)

Max Activating Token Index: 253

Text #2

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.8748. Min Act: -0.1700

Data Index: 6898080 (Open Web Text)

Max Activating Token Index: 182

Text #3

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.8386. Min Act: -0.1700

Data Index: 3198481 (Open Web Text)

Max Activating Token Index: 780

Text #4

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.8122. Min Act: -0.1700

Data Index: 7958798 (Open Web Text)

Max Activating Token Index: 795

Text #5

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.7754. Min Act: -0.1700

Data Index: 5649004 (Open Web Text)

Max Activating Token Index: 823

Text #6

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.7856. Min Act: -0.1700

Data Index: 3140278 (Open Web Text)

Max Activating Token Index: 132

Text #7

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.7291. Min Act: -0.1700

Data Index: 3374860 (Open Web Text)

Max Activating Token Index: 491

Text #8

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.7172. Min Act: -0.1700

Data Index: 1525141 (Open Web Text)

Max Activating Token Index: 170

Text #9

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.7207. Min Act: -0.1700

Data Index: 4285812 (Open Web Text)

Max Activating Token Index: 659

Text #10

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.7637. Min Act: -0.1700

Data Index: 5300130 (Open Web Text)

Max Activating Token Index: 983

Text #11

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.7298. Min Act: -0.1700

Data Index: 1946624 (Open Web Text)

Max Activating Token Index: 945

Text #12

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.7142. Min Act: -0.1700

Data Index: 2608798 (Open Web Text)

Max Activating Token Index: 110

Text #13

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.6642. Min Act: -0.1700

Data Index: 6851190 (Open Web Text)

Max Activating Token Index: 283

Text #14

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.6383. Min Act: -0.1700

Data Index: 3214957 (Open Web Text)

Max Activating Token Index: 722

Text #15

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.6464. Min Act: -0.1700

Data Index: 7405097 (Open Web Text)

Max Activating Token Index: 514

Text #16

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.6433. Min Act: -0.1700

Data Index: 5312710 (Open Web Text)

Max Activating Token Index: 254

Text #17

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.6084. Min Act: -0.1700

Data Index: 5360240 (Open Web Text)

Max Activating Token Index: 68

Text #18

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.5992. Min Act: -0.1700

Data Index: 5158256 (Open Web Text)

Max Activating Token Index: 640

Text #19

Max Range: 5.0286. Min Range: -5.0286

Max Act: 4.6291. Min Act: -0.1700

Data Index: 2327720 (Open Web Text)

Max Activating Token Index: 234