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

Dataset: Open Web Text

Neuron 1435 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: 4.1317. Min Range: -4.1317

Max Act: 4.1317. Min Act: -0.1700

Data Index: 1277548 (Open Web Text)

Max Activating Token Index: 20

Text #1

Max Range: 4.1317. Min Range: -4.1317

Max Act: 4.0971. Min Act: -0.1700

Data Index: 3145536 (Open Web Text)

Max Activating Token Index: 38

Text #2

Max Range: 4.1317. Min Range: -4.1317

Max Act: 4.0287. Min Act: -0.1700

Data Index: 3006424 (Open Web Text)

Max Activating Token Index: 197

Text #3

Max Range: 4.1317. Min Range: -4.1317

Max Act: 4.0053. Min Act: -0.1700

Data Index: 5637976 (Open Web Text)

Max Activating Token Index: 45

Text #4

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.9993. Min Act: -0.1700

Data Index: 7383103 (Open Web Text)

Max Activating Token Index: 78

Text #5

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.9734. Min Act: -0.1700

Data Index: 3145535 (Open Web Text)

Max Activating Token Index: 188

Text #6

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.9841. Min Act: -0.1700

Data Index: 5909340 (Open Web Text)

Max Activating Token Index: 693

Text #7

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.9316. Min Act: -0.1700

Data Index: 550 (Open Web Text)

Max Activating Token Index: 100

Text #8

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.9279. Min Act: -0.1700

Data Index: 3139423 (Open Web Text)

Max Activating Token Index: 137

Text #9

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.9190. Min Act: -0.1700

Data Index: 3145534 (Open Web Text)

Max Activating Token Index: 37

Text #10

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.9442. Min Act: -0.1700

Data Index: 3050015 (Open Web Text)

Max Activating Token Index: 119

Text #11

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.9331. Min Act: -0.1700

Data Index: 8764047 (Open Web Text)

Max Activating Token Index: 467

Text #12

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.9220. Min Act: -0.1700

Data Index: 2990521 (Open Web Text)

Max Activating Token Index: 49

Text #13

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.9416. Min Act: -0.1700

Data Index: 3988714 (Open Web Text)

Max Activating Token Index: 64

Text #14

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.9231. Min Act: -0.1700

Data Index: 5017930 (Open Web Text)

Max Activating Token Index: 85

Text #15

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.9517. Min Act: -0.1700

Data Index: 3467698 (Open Web Text)

Max Activating Token Index: 100

Text #16

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.8921. Min Act: -0.1700

Data Index: 5325226 (Open Web Text)

Max Activating Token Index: 551

Text #17

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.9129. Min Act: -0.1700

Data Index: 1275219 (Open Web Text)

Max Activating Token Index: 455

Text #18

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.9115. Min Act: -0.1700

Data Index: 2284768 (Open Web Text)

Max Activating Token Index: 606

Text #19

Max Range: 4.1317. Min Range: -4.1317

Max Act: 3.9173. Min Act: -0.1700

Data Index: 1672220 (Open Web Text)

Max Activating Token Index: 723