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

Dataset: Open Web Text

Neuron 435 in Layer 2

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: 4.2235. Min Range: -4.2235

Max Act: 4.2235. Min Act: -0.1700

Data Index: 3432198 (Open Web Text)

Max Activating Token Index: 831

Text #1

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.2020. Min Act: -0.1700

Data Index: 3149785 (Open Web Text)

Max Activating Token Index: 272

Text #2

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1847. Min Act: -0.1700

Data Index: 6396567 (Open Web Text)

Max Activating Token Index: 563

Text #3

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1775. Min Act: -0.1700

Data Index: 4739139 (Open Web Text)

Max Activating Token Index: 570

Text #4

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1343. Min Act: -0.1700

Data Index: 5121970 (Open Web Text)

Max Activating Token Index: 181

Text #5

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1484. Min Act: -0.1700

Data Index: 6050554 (Open Web Text)

Max Activating Token Index: 472

Text #6

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1516. Min Act: -0.1700

Data Index: 6224935 (Open Web Text)

Max Activating Token Index: 768

Text #7

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1515. Min Act: -0.1700

Data Index: 8310122 (Open Web Text)

Max Activating Token Index: 740

Text #8

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1339. Min Act: -0.1700

Data Index: 8439475 (Open Web Text)

Max Activating Token Index: 352

Text #9

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1585. Min Act: -0.1700

Data Index: 3433424 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1692. Min Act: -0.1700

Data Index: 7779123 (Open Web Text)

Max Activating Token Index: 130

Text #11

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1378. Min Act: -0.1700

Data Index: 3749169 (Open Web Text)

Max Activating Token Index: 62

Text #12

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1460. Min Act: -0.1700

Data Index: 7197556 (Open Web Text)

Max Activating Token Index: 103

Text #13

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1201. Min Act: -0.1700

Data Index: 4004836 (Open Web Text)

Max Activating Token Index: 356

Text #14

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1200. Min Act: -0.1700

Data Index: 2774054 (Open Web Text)

Max Activating Token Index: 564

Text #15

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1146. Min Act: -0.1700

Data Index: 3978902 (Open Web Text)

Max Activating Token Index: 607

Text #16

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1187. Min Act: -0.1700

Data Index: 143381 (Open Web Text)

Max Activating Token Index: 773

Text #17

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1399. Min Act: -0.1700

Data Index: 2096188 (Open Web Text)

Max Activating Token Index: 320

Text #18

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.0929. Min Act: -0.1700

Data Index: 28905 (Open Web Text)

Max Activating Token Index: 700

Text #19

Max Range: 4.2235. Min Range: -4.2235

Max Act: 4.1299. Min Act: -0.1700

Data Index: 6999548 (Open Web Text)

Max Activating Token Index: 878