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

Dataset: Open Web Text

Neuron 2670 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: 6.2208. Min Range: -6.2208

Max Act: 6.1885. Min Act: -0.1700

Data Index: 6129858 (Open Web Text)

Max Activating Token Index: 497

Text #1

Max Range: 6.2208. Min Range: -6.2208

Max Act: 6.2208. Min Act: -0.1700

Data Index: 1452346 (Open Web Text)

Max Activating Token Index: 680

Text #2

Max Range: 6.2208. Min Range: -6.2208

Max Act: 6.1024. Min Act: -0.1700

Data Index: 2267678 (Open Web Text)

Max Activating Token Index: 728

Text #3

Max Range: 6.2208. Min Range: -6.2208

Max Act: 6.0760. Min Act: -0.1700

Data Index: 612378 (Open Web Text)

Max Activating Token Index: 648

Text #4

Max Range: 6.2208. Min Range: -6.2208

Max Act: 6.0861. Min Act: -0.1700

Data Index: 1203053 (Open Web Text)

Max Activating Token Index: 612

Text #5

Max Range: 6.2208. Min Range: -6.2208

Max Act: 6.0423. Min Act: -0.1700

Data Index: 6311390 (Open Web Text)

Max Activating Token Index: 489

Text #6

Max Range: 6.2208. Min Range: -6.2208

Max Act: 6.0134. Min Act: -0.1700

Data Index: 1638874 (Open Web Text)

Max Activating Token Index: 258

Text #7

Max Range: 6.2208. Min Range: -6.2208

Max Act: 5.9603. Min Act: -0.1700

Data Index: 803687 (Open Web Text)

Max Activating Token Index: 149

Text #8

Max Range: 6.2208. Min Range: -6.2208

Max Act: 5.9238. Min Act: -0.1700

Data Index: 4861295 (Open Web Text)

Max Activating Token Index: 281

Text #9

Max Range: 6.2208. Min Range: -6.2208

Max Act: 5.9541. Min Act: -0.1700

Data Index: 6612743 (Open Web Text)

Max Activating Token Index: 799

Text #10

Max Range: 6.2208. Min Range: -6.2208

Max Act: 5.9116. Min Act: -0.1700

Data Index: 4640199 (Open Web Text)

Max Activating Token Index: 232

Text #11

Max Range: 6.2208. Min Range: -6.2208

Max Act: 5.9319. Min Act: -0.1700

Data Index: 5559311 (Open Web Text)

Max Activating Token Index: 112

Text #12

Max Range: 6.2208. Min Range: -6.2208

Max Act: 5.9373. Min Act: -0.1700

Data Index: 2421810 (Open Web Text)

Max Activating Token Index: 802

Text #13

Max Range: 6.2208. Min Range: -6.2208

Max Act: 5.9102. Min Act: -0.1700

Data Index: 7335704 (Open Web Text)

Max Activating Token Index: 684

Text #14

Max Range: 6.2208. Min Range: -6.2208

Max Act: 5.9043. Min Act: -0.1700

Data Index: 7713279 (Open Web Text)

Max Activating Token Index: 940

Text #15

Max Range: 6.2208. Min Range: -6.2208

Max Act: 5.8921. Min Act: -0.1700

Data Index: 7804548 (Open Web Text)

Max Activating Token Index: 794

Text #16

Max Range: 6.2208. Min Range: -6.2208

Max Act: 5.8805. Min Act: -0.1700

Data Index: 4264214 (Open Web Text)

Max Activating Token Index: 296

Text #17

Max Range: 6.2208. Min Range: -6.2208

Max Act: 5.8564. Min Act: -0.1700

Data Index: 3550904 (Open Web Text)

Max Activating Token Index: 96

Text #18

Max Range: 6.2208. Min Range: -6.2208

Max Act: 5.8857. Min Act: -0.1700

Data Index: 4265338 (Open Web Text)

Max Activating Token Index: 185

Text #19

Max Range: 6.2208. Min Range: -6.2208

Max Act: 5.8699. Min Act: -0.1700

Data Index: 7118579 (Open Web Text)

Max Activating Token Index: 674