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

Dataset: Open Web Text

Neuron 1210 in Layer 3

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: 3.4213. Min Range: -3.4213

Max Act: 3.4213. Min Act: -0.1700

Data Index: 1541131 (Open Web Text)

Max Activating Token Index: 763

Text #1

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.2691. Min Act: -0.1700

Data Index: 7621186 (Open Web Text)

Max Activating Token Index: 497

Text #2

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.3124. Min Act: -0.1700

Data Index: 7818836 (Open Web Text)

Max Activating Token Index: 517

Text #3

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.2517. Min Act: -0.1700

Data Index: 1855855 (Open Web Text)

Max Activating Token Index: 581

Text #4

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.2144. Min Act: -0.1700

Data Index: 2575236 (Open Web Text)

Max Activating Token Index: 446

Text #5

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.2335. Min Act: -0.1700

Data Index: 7247207 (Open Web Text)

Max Activating Token Index: 500

Text #6

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.2401. Min Act: -0.1700

Data Index: 428165 (Open Web Text)

Max Activating Token Index: 368

Text #7

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.1908. Min Act: -0.1700

Data Index: 4911250 (Open Web Text)

Max Activating Token Index: 955

Text #8

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.1888. Min Act: -0.1700

Data Index: 8281504 (Open Web Text)

Max Activating Token Index: 181

Text #9

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.1565. Min Act: -0.1700

Data Index: 1666703 (Open Web Text)

Max Activating Token Index: 731

Text #10

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.1617. Min Act: -0.1700

Data Index: 1007740 (Open Web Text)

Max Activating Token Index: 815

Text #11

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.1591. Min Act: -0.1700

Data Index: 8574345 (Open Web Text)

Max Activating Token Index: 130

Text #12

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.1382. Min Act: -0.1700

Data Index: 2672447 (Open Web Text)

Max Activating Token Index: 231

Text #13

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.1110. Min Act: -0.1700

Data Index: 3828038 (Open Web Text)

Max Activating Token Index: 111

Text #14

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.1454. Min Act: -0.1700

Data Index: 2566668 (Open Web Text)

Max Activating Token Index: 437

Text #15

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.0831. Min Act: -0.1700

Data Index: 8493423 (Open Web Text)

Max Activating Token Index: 721

Text #16

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.1163. Min Act: -0.1700

Data Index: 5089543 (Open Web Text)

Max Activating Token Index: 797

Text #17

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.1281. Min Act: -0.1700

Data Index: 5327117 (Open Web Text)

Max Activating Token Index: 733

Text #18

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.1724. Min Act: -0.1700

Data Index: 393910 (Open Web Text)

Max Activating Token Index: 590

Text #19

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.0916. Min Act: -0.1700

Data Index: 8025697 (Open Web Text)

Max Activating Token Index: 785