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

Dataset: Open Web Text

Neuron 2439 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: 5.4227. Min Range: -5.4227

Max Act: 5.4227. Min Act: -0.1700

Data Index: 6328608 (Open Web Text)

Max Activating Token Index: 849

Text #1

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.4216. Min Act: -0.1700

Data Index: 3980019 (Open Web Text)

Max Activating Token Index: 153

Text #2

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.3930. Min Act: -0.1700

Data Index: 3750194 (Open Web Text)

Max Activating Token Index: 376

Text #3

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.3401. Min Act: -0.1700

Data Index: 2382956 (Open Web Text)

Max Activating Token Index: 452

Text #4

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.3184. Min Act: -0.1700

Data Index: 5820276 (Open Web Text)

Max Activating Token Index: 708

Text #5

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.2429. Min Act: -0.1700

Data Index: 5968157 (Open Web Text)

Max Activating Token Index: 663

Text #6

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.2875. Min Act: -0.1700

Data Index: 2835914 (Open Web Text)

Max Activating Token Index: 903

Text #7

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.2148. Min Act: -0.1700

Data Index: 308514 (Open Web Text)

Max Activating Token Index: 298

Text #8

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.1854. Min Act: -0.1700

Data Index: 1263749 (Open Web Text)

Max Activating Token Index: 549

Text #9

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.2011. Min Act: -0.1700

Data Index: 6511026 (Open Web Text)

Max Activating Token Index: 278

Text #10

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.1218. Min Act: -0.1700

Data Index: 5820281 (Open Web Text)

Max Activating Token Index: 650

Text #11

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.1509. Min Act: -0.1700

Data Index: 8340107 (Open Web Text)

Max Activating Token Index: 234

Text #12

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.1394. Min Act: -0.1700

Data Index: 1263739 (Open Web Text)

Max Activating Token Index: 932

Text #13

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.1600. Min Act: -0.1700

Data Index: 5264952 (Open Web Text)

Max Activating Token Index: 192

Text #14

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.1239. Min Act: -0.1700

Data Index: 5481885 (Open Web Text)

Max Activating Token Index: 276

Text #15

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.1724. Min Act: -0.1700

Data Index: 5820277 (Open Web Text)

Max Activating Token Index: 551

Text #16

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.0781. Min Act: -0.1700

Data Index: 3131304 (Open Web Text)

Max Activating Token Index: 190

Text #17

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.0870. Min Act: -0.1700

Data Index: 5626810 (Open Web Text)

Max Activating Token Index: 479

Text #18

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.1034. Min Act: -0.1700

Data Index: 6677577 (Open Web Text)

Max Activating Token Index: 309

Text #19

Max Range: 5.4227. Min Range: -5.4227

Max Act: 5.0577. Min Act: -0.1700

Data Index: 1263758 (Open Web Text)

Max Activating Token Index: 273