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

Dataset: Open Web Text

Neuron 1882 in Layer 1

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: 3.2494. Min Range: -3.2494

Max Act: 3.2494. Min Act: -0.1700

Data Index: 4890036 (Open Web Text)

Max Activating Token Index: 428

Text #1

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.2052. Min Act: -0.1700

Data Index: 3770078 (Open Web Text)

Max Activating Token Index: 708

Text #2

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1932. Min Act: -0.1700

Data Index: 5103351 (Open Web Text)

Max Activating Token Index: 668

Text #3

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1762. Min Act: -0.1700

Data Index: 1872573 (Open Web Text)

Max Activating Token Index: 487

Text #4

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1680. Min Act: -0.1700

Data Index: 4082463 (Open Web Text)

Max Activating Token Index: 716

Text #5

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1623. Min Act: -0.1700

Data Index: 31864 (Open Web Text)

Max Activating Token Index: 176

Text #6

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1731. Min Act: -0.1700

Data Index: 1566691 (Open Web Text)

Max Activating Token Index: 179

Text #7

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1589. Min Act: -0.1700

Data Index: 3008829 (Open Web Text)

Max Activating Token Index: 551

Text #8

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1396. Min Act: -0.1700

Data Index: 4625919 (Open Web Text)

Max Activating Token Index: 339

Text #9

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1436. Min Act: -0.1700

Data Index: 8102584 (Open Web Text)

Max Activating Token Index: 131

Text #10

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1588. Min Act: -0.1700

Data Index: 1326163 (Open Web Text)

Max Activating Token Index: 991

Text #11

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1463. Min Act: -0.1700

Data Index: 399864 (Open Web Text)

Max Activating Token Index: 86

Text #12

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1398. Min Act: -0.1700

Data Index: 4795464 (Open Web Text)

Max Activating Token Index: 149

Text #13

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1330. Min Act: -0.1700

Data Index: 8481304 (Open Web Text)

Max Activating Token Index: 950

Text #14

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1190. Min Act: -0.1700

Data Index: 1194917 (Open Web Text)

Max Activating Token Index: 543

Text #15

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1166. Min Act: -0.1700

Data Index: 206299 (Open Web Text)

Max Activating Token Index: 765

Text #16

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1282. Min Act: -0.1700

Data Index: 4036027 (Open Web Text)

Max Activating Token Index: 141

Text #17

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1243. Min Act: -0.1700

Data Index: 1748497 (Open Web Text)

Max Activating Token Index: 95

Text #18

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1247. Min Act: -0.1700

Data Index: 5458763 (Open Web Text)

Max Activating Token Index: 783

Text #19

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1248. Min Act: -0.1700

Data Index: 7805606 (Open Web Text)

Max Activating Token Index: 198