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

Dataset: Open Web Text

Neuron 2376 in Layer 6

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: 3.7066. Min Range: -3.7066

Max Act: 3.7066. Min Act: -0.1700

Data Index: 8505403 (Open Web Text)

Max Activating Token Index: 574

Text #1

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.6935. Min Act: -0.1700

Data Index: 1700288 (Open Web Text)

Max Activating Token Index: 262

Text #2

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.6678. Min Act: -0.1700

Data Index: 740105 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.6452. Min Act: -0.1700

Data Index: 5687007 (Open Web Text)

Max Activating Token Index: 660

Text #4

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.6691. Min Act: -0.1700

Data Index: 6908721 (Open Web Text)

Max Activating Token Index: 830

Text #5

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.6323. Min Act: -0.1700

Data Index: 8102842 (Open Web Text)

Max Activating Token Index: 553

Text #6

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.6234. Min Act: -0.1700

Data Index: 2737993 (Open Web Text)

Max Activating Token Index: 48

Text #7

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.6202. Min Act: -0.1700

Data Index: 3519153 (Open Web Text)

Max Activating Token Index: 166

Text #8

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.5982. Min Act: -0.1700

Data Index: 6229604 (Open Web Text)

Max Activating Token Index: 871

Text #9

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.5475. Min Act: -0.1700

Data Index: 1982482 (Open Web Text)

Max Activating Token Index: 304

Text #10

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.5465. Min Act: -0.1700

Data Index: 8660734 (Open Web Text)

Max Activating Token Index: 913

Text #11

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.5265. Min Act: -0.1700

Data Index: 3340123 (Open Web Text)

Max Activating Token Index: 640

Text #12

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.5523. Min Act: -0.1700

Data Index: 4562752 (Open Web Text)

Max Activating Token Index: 620

Text #13

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.5365. Min Act: -0.1700

Data Index: 7457585 (Open Web Text)

Max Activating Token Index: 514

Text #14

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.5208. Min Act: -0.1700

Data Index: 1879146 (Open Web Text)

Max Activating Token Index: 201

Text #15

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.5184. Min Act: -0.1700

Data Index: 3505023 (Open Web Text)

Max Activating Token Index: 232

Text #16

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.5381. Min Act: -0.1700

Data Index: 4636135 (Open Web Text)

Max Activating Token Index: 393

Text #17

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.5142. Min Act: -0.1700

Data Index: 5083848 (Open Web Text)

Max Activating Token Index: 430

Text #18

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.5091. Min Act: -0.1700

Data Index: 5654313 (Open Web Text)

Max Activating Token Index: 107

Text #19

Max Range: 3.7066. Min Range: -3.7066

Max Act: 3.5090. Min Act: -0.1700

Data Index: 3619846 (Open Web Text)

Max Activating Token Index: 805