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

Dataset: Open Web Text

Neuron 1445 in Layer 1

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: 1.6338. Min Range: -1.6338

Max Act: 1.6338. Min Act: -0.1700

Data Index: 948802 (Open Web Text)

Max Activating Token Index: 671

Text #1

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.6239. Min Act: -0.1700

Data Index: 6319464 (Open Web Text)

Max Activating Token Index: 122

Text #2

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5668. Min Act: -0.1700

Data Index: 2360804 (Open Web Text)

Max Activating Token Index: 500

Text #3

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5808. Min Act: -0.1700

Data Index: 5518154 (Open Web Text)

Max Activating Token Index: 547

Text #4

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5606. Min Act: -0.1700

Data Index: 3834875 (Open Web Text)

Max Activating Token Index: 262

Text #5

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5545. Min Act: -0.1700

Data Index: 577953 (Open Web Text)

Max Activating Token Index: 728

Text #6

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5518. Min Act: -0.1700

Data Index: 5101517 (Open Web Text)

Max Activating Token Index: 412

Text #7

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5629. Min Act: -0.1700

Data Index: 8701828 (Open Web Text)

Max Activating Token Index: 595

Text #8

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5558. Min Act: -0.1700

Data Index: 8416779 (Open Web Text)

Max Activating Token Index: 83

Text #9

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5370. Min Act: -0.1700

Data Index: 7858916 (Open Web Text)

Max Activating Token Index: 812

Text #10

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5443. Min Act: -0.1689

Data Index: 3978731 (Open Web Text)

Max Activating Token Index: 614

Text #11

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5304. Min Act: -0.1700

Data Index: 2360805 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5404. Min Act: -0.1700

Data Index: 7442710 (Open Web Text)

Max Activating Token Index: 614

Text #13

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5297. Min Act: -0.1700

Data Index: 3214862 (Open Web Text)

Max Activating Token Index: 333

Text #14

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5298. Min Act: -0.1700

Data Index: 2871894 (Open Web Text)

Max Activating Token Index: 440

Text #15

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5287. Min Act: -0.1700

Data Index: 3507455 (Open Web Text)

Max Activating Token Index: 213

Text #16

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5300. Min Act: -0.1700

Data Index: 3971190 (Open Web Text)

Max Activating Token Index: 596

Text #17

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5249. Min Act: -0.1700

Data Index: 5795038 (Open Web Text)

Max Activating Token Index: 752

Text #18

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5297. Min Act: -0.1700

Data Index: 5202903 (Open Web Text)

Max Activating Token Index: 799

Text #19

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5241. Min Act: -0.1700

Data Index: 4121535 (Open Web Text)

Max Activating Token Index: 739