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

Dataset: Open Web Text

Neuron 267 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: 0.8945. Min Range: -0.8945

Max Act: 0.8945. Min Act: -0.1700

Data Index: 1702438 (Open Web Text)

Max Activating Token Index: 817

Text #1

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8643. Min Act: -0.1700

Data Index: 817072 (Open Web Text)

Max Activating Token Index: 583

Text #2

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8406. Min Act: -0.1700

Data Index: 5168436 (Open Web Text)

Max Activating Token Index: 259

Text #3

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8393. Min Act: -0.1700

Data Index: 4872889 (Open Web Text)

Max Activating Token Index: 179

Text #4

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8381. Min Act: -0.1700

Data Index: 1010446 (Open Web Text)

Max Activating Token Index: 385

Text #5

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8224. Min Act: -0.1700

Data Index: 7973006 (Open Web Text)

Max Activating Token Index: 609

Text #6

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8116. Min Act: -0.1700

Data Index: 2936927 (Open Web Text)

Max Activating Token Index: 843

Text #7

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8186. Min Act: -0.1700

Data Index: 7046830 (Open Web Text)

Max Activating Token Index: 323

Text #8

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8114. Min Act: -0.1700

Data Index: 338587 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8144. Min Act: -0.1700

Data Index: 3179519 (Open Web Text)

Max Activating Token Index: 107

Text #10

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8034. Min Act: -0.1700

Data Index: 15969 (Open Web Text)

Max Activating Token Index: 353

Text #11

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8012. Min Act: -0.1700

Data Index: 3123608 (Open Web Text)

Max Activating Token Index: 571

Text #12

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7962. Min Act: -0.1700

Data Index: 8190837 (Open Web Text)

Max Activating Token Index: 258

Text #13

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7873. Min Act: -0.1700

Data Index: 8194399 (Open Web Text)

Max Activating Token Index: 903

Text #14

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7840. Min Act: -0.1700

Data Index: 8533305 (Open Web Text)

Max Activating Token Index: 329

Text #15

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7944. Min Act: -0.1700

Data Index: 2650731 (Open Web Text)

Max Activating Token Index: 120

Text #16

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7921. Min Act: -0.1700

Data Index: 920496 (Open Web Text)

Max Activating Token Index: 111

Text #17

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7874. Min Act: -0.1700

Data Index: 5488644 (Open Web Text)

Max Activating Token Index: 186

Text #18

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7798. Min Act: -0.1700

Data Index: 3291956 (Open Web Text)

Max Activating Token Index: 854

Text #19

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7906. Min Act: -0.1700

Data Index: 1853359 (Open Web Text)

Max Activating Token Index: 580