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

Dataset: Open Web Text

Neuron 1162 in Layer 4

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: 3.1738. Min Range: -3.1738

Max Act: 3.1738. Min Act: -0.1700

Data Index: 5289268 (Open Web Text)

Max Activating Token Index: 282

Text #1

Max Range: 3.1738. Min Range: -3.1738

Max Act: 3.1131. Min Act: -0.1700

Data Index: 1114837 (Open Web Text)

Max Activating Token Index: 353

Text #2

Max Range: 3.1738. Min Range: -3.1738

Max Act: 3.0313. Min Act: -0.1700

Data Index: 2606722 (Open Web Text)

Max Activating Token Index: 292

Text #3

Max Range: 3.1738. Min Range: -3.1738

Max Act: 3.0182. Min Act: -0.1700

Data Index: 771642 (Open Web Text)

Max Activating Token Index: 478

Text #4

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.9869. Min Act: -0.1700

Data Index: 8065218 (Open Web Text)

Max Activating Token Index: 886

Text #5

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.9784. Min Act: -0.1700

Data Index: 4219905 (Open Web Text)

Max Activating Token Index: 485

Text #6

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.9547. Min Act: -0.1700

Data Index: 5270938 (Open Web Text)

Max Activating Token Index: 729

Text #7

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.9205. Min Act: -0.1700

Data Index: 5307421 (Open Web Text)

Max Activating Token Index: 337

Text #8

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.9410. Min Act: -0.1700

Data Index: 7571330 (Open Web Text)

Max Activating Token Index: 527

Text #9

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.9317. Min Act: -0.1700

Data Index: 6393299 (Open Web Text)

Max Activating Token Index: 117

Text #10

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.9214. Min Act: -0.1700

Data Index: 758639 (Open Web Text)

Max Activating Token Index: 278

Text #11

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.9232. Min Act: -0.1700

Data Index: 1826199 (Open Web Text)

Max Activating Token Index: 920

Text #12

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.9421. Min Act: -0.1700

Data Index: 8363938 (Open Web Text)

Max Activating Token Index: 856

Text #13

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.8854. Min Act: -0.1700

Data Index: 6869855 (Open Web Text)

Max Activating Token Index: 397

Text #14

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.9033. Min Act: -0.1700

Data Index: 4510908 (Open Web Text)

Max Activating Token Index: 908

Text #15

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.9038. Min Act: -0.1700

Data Index: 7296492 (Open Web Text)

Max Activating Token Index: 743

Text #16

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.8509. Min Act: -0.1700

Data Index: 1753495 (Open Web Text)

Max Activating Token Index: 764

Text #17

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.8935. Min Act: -0.1700

Data Index: 6904096 (Open Web Text)

Max Activating Token Index: 533

Text #18

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.8829. Min Act: -0.1700

Data Index: 6406700 (Open Web Text)

Max Activating Token Index: 790

Text #19

Max Range: 3.1738. Min Range: -3.1738

Max Act: 2.8893. Min Act: -0.1700

Data Index: 298193 (Open Web Text)

Max Activating Token Index: 101