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

Dataset: Open Web Text

Neuron 1886 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: 1.1846. Min Range: -1.1846

Max Act: 1.1846. Min Act: -0.1692

Data Index: 6666887 (Open Web Text)

Max Activating Token Index: 100

Text #1

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1584. Min Act: -0.1700

Data Index: 6666886 (Open Web Text)

Max Activating Token Index: 961

Text #2

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1667. Min Act: -0.1695

Data Index: 3056175 (Open Web Text)

Max Activating Token Index: 112

Text #3

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1618. Min Act: -0.1700

Data Index: 8234259 (Open Web Text)

Max Activating Token Index: 49

Text #4

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1450. Min Act: -0.1700

Data Index: 673630 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1421. Min Act: -0.1700

Data Index: 7211622 (Open Web Text)

Max Activating Token Index: 577

Text #6

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1467. Min Act: -0.1680

Data Index: 5353567 (Open Web Text)

Max Activating Token Index: 130

Text #7

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1353. Min Act: -0.1700

Data Index: 625654 (Open Web Text)

Max Activating Token Index: 828

Text #8

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1227. Min Act: -0.1698

Data Index: 104437 (Open Web Text)

Max Activating Token Index: 386

Text #9

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1186. Min Act: -0.1356

Data Index: 1495706 (Open Web Text)

Max Activating Token Index: 675

Text #10

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1031. Min Act: -0.1664

Data Index: 383889 (Open Web Text)

Max Activating Token Index: 229

Text #11

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1113. Min Act: -0.1698

Data Index: 8237300 (Open Web Text)

Max Activating Token Index: 931

Text #12

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0893. Min Act: -0.1700

Data Index: 8307268 (Open Web Text)

Max Activating Token Index: 576

Text #13

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0858. Min Act: -0.1693

Data Index: 7176176 (Open Web Text)

Max Activating Token Index: 397

Text #14

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0783. Min Act: -0.1699

Data Index: 2244925 (Open Web Text)

Max Activating Token Index: 465

Text #15

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0686. Min Act: -0.1672

Data Index: 3982861 (Open Web Text)

Max Activating Token Index: 749

Text #16

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0716. Min Act: -0.1680

Data Index: 4158600 (Open Web Text)

Max Activating Token Index: 206

Text #17

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0756. Min Act: -0.1646

Data Index: 2318140 (Open Web Text)

Max Activating Token Index: 595

Text #18

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0681. Min Act: -0.1688

Data Index: 1119412 (Open Web Text)

Max Activating Token Index: 199

Text #19

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0709. Min Act: -0.1700

Data Index: 363814 (Open Web Text)

Max Activating Token Index: 518