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

Dataset: Open Web Text

Neuron 2426 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: 3.0908. Min Range: -3.0908

Max Act: 3.0908. Min Act: -0.1700

Data Index: 3188950 (Open Web Text)

Max Activating Token Index: 348

Text #1

Max Range: 3.0908. Min Range: -3.0908

Max Act: 3.0480. Min Act: -0.1700

Data Index: 264206 (Open Web Text)

Max Activating Token Index: 484

Text #2

Max Range: 3.0908. Min Range: -3.0908

Max Act: 3.0140. Min Act: -0.1700

Data Index: 6151213 (Open Web Text)

Max Activating Token Index: 692

Text #3

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.9916. Min Act: -0.1700

Data Index: 5542890 (Open Web Text)

Max Activating Token Index: 131

Text #4

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.9958. Min Act: -0.1700

Data Index: 8035997 (Open Web Text)

Max Activating Token Index: 978

Text #5

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.9717. Min Act: -0.1700

Data Index: 633281 (Open Web Text)

Max Activating Token Index: 405

Text #6

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.9247. Min Act: -0.1700

Data Index: 1995356 (Open Web Text)

Max Activating Token Index: 772

Text #7

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.9693. Min Act: -0.1700

Data Index: 2215522 (Open Web Text)

Max Activating Token Index: 890

Text #8

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.9593. Min Act: -0.1700

Data Index: 7768164 (Open Web Text)

Max Activating Token Index: 855

Text #9

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.9416. Min Act: -0.1700

Data Index: 1368825 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.9484. Min Act: -0.1700

Data Index: 715659 (Open Web Text)

Max Activating Token Index: 374

Text #11

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.9209. Min Act: -0.1700

Data Index: 8640108 (Open Web Text)

Max Activating Token Index: 226

Text #12

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.9200. Min Act: -0.1700

Data Index: 8656137 (Open Web Text)

Max Activating Token Index: 518

Text #13

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.9203. Min Act: -0.1700

Data Index: 3492807 (Open Web Text)

Max Activating Token Index: 159

Text #14

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.9332. Min Act: -0.1700

Data Index: 7136216 (Open Web Text)

Max Activating Token Index: 993

Text #15

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.9046. Min Act: -0.1700

Data Index: 136404 (Open Web Text)

Max Activating Token Index: 262

Text #16

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.8757. Min Act: -0.1700

Data Index: 7745478 (Open Web Text)

Max Activating Token Index: 636

Text #17

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.9096. Min Act: -0.1700

Data Index: 1153809 (Open Web Text)

Max Activating Token Index: 762

Text #18

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.8705. Min Act: -0.1700

Data Index: 2991402 (Open Web Text)

Max Activating Token Index: 1010

Text #19

Max Range: 3.0908. Min Range: -3.0908

Max Act: 2.8962. Min Act: -0.1700

Data Index: 438499 (Open Web Text)

Max Activating Token Index: 855