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

Dataset: Open Web Text

Neuron 1093 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: 4.1287. Min Range: -4.1287

Max Act: 4.1287. Min Act: -0.1700

Data Index: 7049919 (Open Web Text)

Max Activating Token Index: 908

Text #1

Max Range: 4.1287. Min Range: -4.1287

Max Act: 4.0745. Min Act: -0.1700

Data Index: 4465235 (Open Web Text)

Max Activating Token Index: 145

Text #2

Max Range: 4.1287. Min Range: -4.1287

Max Act: 4.0027. Min Act: -0.1700

Data Index: 4254869 (Open Web Text)

Max Activating Token Index: 925

Text #3

Max Range: 4.1287. Min Range: -4.1287

Max Act: 4.0251. Min Act: -0.1700

Data Index: 7049912 (Open Web Text)

Max Activating Token Index: 43

Text #4

Max Range: 4.1287. Min Range: -4.1287

Max Act: 4.0081. Min Act: -0.1700

Data Index: 7346397 (Open Web Text)

Max Activating Token Index: 481

Text #5

Max Range: 4.1287. Min Range: -4.1287

Max Act: 3.9705. Min Act: -0.1700

Data Index: 59680 (Open Web Text)

Max Activating Token Index: 623

Text #6

Max Range: 4.1287. Min Range: -4.1287

Max Act: 3.9699. Min Act: -0.1700

Data Index: 5618173 (Open Web Text)

Max Activating Token Index: 326

Text #7

Max Range: 4.1287. Min Range: -4.1287

Max Act: 3.9389. Min Act: -0.1700

Data Index: 4731593 (Open Web Text)

Max Activating Token Index: 472

Text #8

Max Range: 4.1287. Min Range: -4.1287

Max Act: 3.8760. Min Act: -0.1700

Data Index: 896783 (Open Web Text)

Max Activating Token Index: 161

Text #9

Max Range: 4.1287. Min Range: -4.1287

Max Act: 3.9309. Min Act: -0.1700

Data Index: 1423022 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 4.1287. Min Range: -4.1287

Max Act: 3.9472. Min Act: -0.1700

Data Index: 1590905 (Open Web Text)

Max Activating Token Index: 674

Text #11

Max Range: 4.1287. Min Range: -4.1287

Max Act: 3.9234. Min Act: -0.1700

Data Index: 4254870 (Open Web Text)

Max Activating Token Index: 799

Text #12

Max Range: 4.1287. Min Range: -4.1287

Max Act: 3.9483. Min Act: -0.1700

Data Index: 1642815 (Open Web Text)

Max Activating Token Index: 28

Text #13

Max Range: 4.1287. Min Range: -4.1287

Max Act: 3.9263. Min Act: -0.1700

Data Index: 716595 (Open Web Text)

Max Activating Token Index: 51

Text #14

Max Range: 4.1287. Min Range: -4.1287

Max Act: 3.9444. Min Act: -0.1700

Data Index: 7294692 (Open Web Text)

Max Activating Token Index: 508

Text #15

Max Range: 4.1287. Min Range: -4.1287

Max Act: 3.9157. Min Act: -0.1700

Data Index: 2225140 (Open Web Text)

Max Activating Token Index: 59

Text #16

Max Range: 4.1287. Min Range: -4.1287

Max Act: 3.9306. Min Act: -0.1700

Data Index: 4947178 (Open Web Text)

Max Activating Token Index: 271

Text #17

Max Range: 4.1287. Min Range: -4.1287

Max Act: 3.8869. Min Act: -0.1700

Data Index: 5337629 (Open Web Text)

Max Activating Token Index: 985

Text #18

Max Range: 4.1287. Min Range: -4.1287

Max Act: 3.9517. Min Act: -0.1700

Data Index: 5380877 (Open Web Text)

Max Activating Token Index: 558

Text #19

Max Range: 4.1287. Min Range: -4.1287

Max Act: 3.8761. Min Act: -0.1700

Data Index: 5423961 (Open Web Text)

Max Activating Token Index: 1007