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

Dataset: Open Web Text

Neuron 2349 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: 1.2460. Min Range: -1.2460

Max Act: 1.2460. Min Act: -0.1495

Data Index: 574977 (Open Web Text)

Max Activating Token Index: 744

Text #1

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1779. Min Act: -0.1496

Data Index: 5997952 (Open Web Text)

Max Activating Token Index: 716

Text #2

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1565. Min Act: -0.1325

Data Index: 7189028 (Open Web Text)

Max Activating Token Index: 585

Text #3

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1476. Min Act: -0.1516

Data Index: 350652 (Open Web Text)

Max Activating Token Index: 444

Text #4

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1304. Min Act: -0.1155

Data Index: 2128103 (Open Web Text)

Max Activating Token Index: 844

Text #5

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1387. Min Act: -0.1237

Data Index: 7151715 (Open Web Text)

Max Activating Token Index: 778

Text #6

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1453. Min Act: -0.1697

Data Index: 5147281 (Open Web Text)

Max Activating Token Index: 788

Text #7

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1278. Min Act: -0.1357

Data Index: 2566636 (Open Web Text)

Max Activating Token Index: 759

Text #8

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1296. Min Act: -0.1296

Data Index: 2983298 (Open Web Text)

Max Activating Token Index: 820

Text #9

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1255. Min Act: -0.1580

Data Index: 4385197 (Open Web Text)

Max Activating Token Index: 722

Text #10

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1232. Min Act: -0.1694

Data Index: 4605582 (Open Web Text)

Max Activating Token Index: 702

Text #11

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1278. Min Act: -0.1692

Data Index: 1556205 (Open Web Text)

Max Activating Token Index: 242

Text #12

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1269. Min Act: -0.1442

Data Index: 7217790 (Open Web Text)

Max Activating Token Index: 884

Text #13

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1231. Min Act: -0.1448

Data Index: 3946623 (Open Web Text)

Max Activating Token Index: 753

Text #14

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1217. Min Act: -0.1513

Data Index: 2961225 (Open Web Text)

Max Activating Token Index: 609

Text #15

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1204. Min Act: -0.1643

Data Index: 6647275 (Open Web Text)

Max Activating Token Index: 685

Text #16

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1105. Min Act: -0.1535

Data Index: 3803229 (Open Web Text)

Max Activating Token Index: 844

Text #17

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1159. Min Act: -0.1544

Data Index: 1521136 (Open Web Text)

Max Activating Token Index: 713

Text #18

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1202. Min Act: -0.1550

Data Index: 4585269 (Open Web Text)

Max Activating Token Index: 789

Text #19

Max Range: 1.2460. Min Range: -1.2460

Max Act: 1.1239. Min Act: -0.1389

Data Index: 1140747 (Open Web Text)

Max Activating Token Index: 757