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

Dataset: Open Web Text

Neuron 355 in Layer 3

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: 1.6349. Min Range: -1.6349

Max Act: 1.6349. Min Act: -0.1677

Data Index: 4744187 (Open Web Text)

Max Activating Token Index: 124

Text #1

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.6226. Min Act: -0.1698

Data Index: 5007827 (Open Web Text)

Max Activating Token Index: 21

Text #2

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.6042. Min Act: -0.1694

Data Index: 5105745 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.5968. Min Act: -0.1698

Data Index: 4744184 (Open Web Text)

Max Activating Token Index: 285

Text #4

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.6012. Min Act: -0.1680

Data Index: 186779 (Open Web Text)

Max Activating Token Index: 113

Text #5

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.5819. Min Act: -0.1700

Data Index: 6955892 (Open Web Text)

Max Activating Token Index: 884

Text #6

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.5537. Min Act: -0.1654

Data Index: 8693412 (Open Web Text)

Max Activating Token Index: 78

Text #7

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.5461. Min Act: -0.1697

Data Index: 7683644 (Open Web Text)

Max Activating Token Index: 650

Text #8

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.5495. Min Act: -0.1698

Data Index: 5455969 (Open Web Text)

Max Activating Token Index: 83

Text #9

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.5409. Min Act: -0.1700

Data Index: 6683527 (Open Web Text)

Max Activating Token Index: 874

Text #10

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.5318. Min Act: -0.1697

Data Index: 6123756 (Open Web Text)

Max Activating Token Index: 771

Text #11

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.5213. Min Act: -0.1698

Data Index: 2061410 (Open Web Text)

Max Activating Token Index: 588

Text #12

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.5250. Min Act: -0.1697

Data Index: 4325140 (Open Web Text)

Max Activating Token Index: 34

Text #13

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.5213. Min Act: -0.1700

Data Index: 6942307 (Open Web Text)

Max Activating Token Index: 518

Text #14

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.5282. Min Act: -0.1700

Data Index: 6606512 (Open Web Text)

Max Activating Token Index: 345

Text #15

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.5208. Min Act: -0.1695

Data Index: 5799906 (Open Web Text)

Max Activating Token Index: 140

Text #16

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.5178. Min Act: -0.1700

Data Index: 7655235 (Open Web Text)

Max Activating Token Index: 290

Text #17

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.4930. Min Act: -0.1682

Data Index: 8709639 (Open Web Text)

Max Activating Token Index: 726

Text #18

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.5031. Min Act: -0.1699

Data Index: 8316648 (Open Web Text)

Max Activating Token Index: 369

Text #19

Max Range: 1.6349. Min Range: -1.6349

Max Act: 1.5008. Min Act: -0.1697

Data Index: 4362646 (Open Web Text)

Max Activating Token Index: 123