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

Dataset: Open Web Text

Neuron 490 in Layer 2

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: 3.0856. Min Range: -3.0856

Max Act: 3.0856. Min Act: -0.1700

Data Index: 1231079 (Open Web Text)

Max Activating Token Index: 567

Text #1

Max Range: 3.0856. Min Range: -3.0856

Max Act: 3.0138. Min Act: -0.1700

Data Index: 1396729 (Open Web Text)

Max Activating Token Index: 890

Text #2

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9525. Min Act: -0.1700

Data Index: 7060511 (Open Web Text)

Max Activating Token Index: 962

Text #3

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9725. Min Act: -0.1700

Data Index: 7193909 (Open Web Text)

Max Activating Token Index: 202

Text #4

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9600. Min Act: -0.1700

Data Index: 5966133 (Open Web Text)

Max Activating Token Index: 203

Text #5

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9694. Min Act: -0.1700

Data Index: 1919821 (Open Web Text)

Max Activating Token Index: 464

Text #6

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9662. Min Act: -0.1700

Data Index: 253681 (Open Web Text)

Max Activating Token Index: 948

Text #7

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9446. Min Act: -0.1700

Data Index: 3973677 (Open Web Text)

Max Activating Token Index: 228

Text #8

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9479. Min Act: -0.1700

Data Index: 5207991 (Open Web Text)

Max Activating Token Index: 987

Text #9

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9574. Min Act: -0.1700

Data Index: 4091970 (Open Web Text)

Max Activating Token Index: 558

Text #10

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9484. Min Act: -0.1700

Data Index: 2977701 (Open Web Text)

Max Activating Token Index: 424

Text #11

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9023. Min Act: -0.1700

Data Index: 1864415 (Open Web Text)

Max Activating Token Index: 224

Text #12

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9148. Min Act: -0.1700

Data Index: 3561037 (Open Web Text)

Max Activating Token Index: 949

Text #13

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9030. Min Act: -0.1700

Data Index: 1519996 (Open Web Text)

Max Activating Token Index: 904

Text #14

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9130. Min Act: -0.1700

Data Index: 46349 (Open Web Text)

Max Activating Token Index: 256

Text #15

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9256. Min Act: -0.1700

Data Index: 8786062 (Open Web Text)

Max Activating Token Index: 495

Text #16

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9081. Min Act: -0.1700

Data Index: 7872434 (Open Web Text)

Max Activating Token Index: 386

Text #17

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9110. Min Act: -0.1700

Data Index: 1033080 (Open Web Text)

Max Activating Token Index: 300

Text #18

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9024. Min Act: -0.1700

Data Index: 5800978 (Open Web Text)

Max Activating Token Index: 144

Text #19

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.8997. Min Act: -0.1700

Data Index: 1579123 (Open Web Text)

Max Activating Token Index: 592