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

Dataset: Open Web Text

Neuron 216 in Layer 4

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: 3.8888. Min Range: -3.8888

Max Act: 3.8888. Min Act: -0.1700

Data Index: 1732440 (Open Web Text)

Max Activating Token Index: 34

Text #1

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.8043. Min Act: -0.1700

Data Index: 4730612 (Open Web Text)

Max Activating Token Index: 580

Text #2

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.8043. Min Act: -0.1700

Data Index: 6606974 (Open Web Text)

Max Activating Token Index: 532

Text #3

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.7921. Min Act: -0.1700

Data Index: 1102468 (Open Web Text)

Max Activating Token Index: 839

Text #4

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.7426. Min Act: -0.1700

Data Index: 8787813 (Open Web Text)

Max Activating Token Index: 424

Text #5

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.7413. Min Act: -0.1700

Data Index: 2958113 (Open Web Text)

Max Activating Token Index: 537

Text #6

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.7534. Min Act: -0.1700

Data Index: 3147051 (Open Web Text)

Max Activating Token Index: 258

Text #7

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.7795. Min Act: -0.1700

Data Index: 6489452 (Open Web Text)

Max Activating Token Index: 914

Text #8

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.7655. Min Act: -0.1700

Data Index: 7673543 (Open Web Text)

Max Activating Token Index: 281

Text #9

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.7877. Min Act: -0.1700

Data Index: 3485031 (Open Web Text)

Max Activating Token Index: 488

Text #10

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.7221. Min Act: -0.1700

Data Index: 7421370 (Open Web Text)

Max Activating Token Index: 607

Text #11

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.7234. Min Act: -0.1700

Data Index: 3470520 (Open Web Text)

Max Activating Token Index: 240

Text #12

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.7093. Min Act: -0.1700

Data Index: 6080167 (Open Web Text)

Max Activating Token Index: 959

Text #13

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.7215. Min Act: -0.1700

Data Index: 4403391 (Open Web Text)

Max Activating Token Index: 832

Text #14

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.7206. Min Act: -0.1700

Data Index: 8683604 (Open Web Text)

Max Activating Token Index: 391

Text #15

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.7023. Min Act: -0.1700

Data Index: 5084032 (Open Web Text)

Max Activating Token Index: 871

Text #16

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.7065. Min Act: -0.1700

Data Index: 964960 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.6850. Min Act: -0.1700

Data Index: 7432722 (Open Web Text)

Max Activating Token Index: 956

Text #18

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.7013. Min Act: -0.1700

Data Index: 189684 (Open Web Text)

Max Activating Token Index: 322

Text #19

Max Range: 3.8888. Min Range: -3.8888

Max Act: 3.6664. Min Act: -0.1700

Data Index: 6725208 (Open Web Text)

Max Activating Token Index: 32