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

Dataset: Open Web Text

Neuron 1383 in Layer 5

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: 3.5056. Min Range: -3.5056

Max Act: 3.5056. Min Act: -0.1700

Data Index: 8043818 (Open Web Text)

Max Activating Token Index: 292

Text #1

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.2965. Min Act: -0.1700

Data Index: 3978157 (Open Web Text)

Max Activating Token Index: 50

Text #2

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.2892. Min Act: -0.1700

Data Index: 2144102 (Open Web Text)

Max Activating Token Index: 935

Text #3

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.3103. Min Act: -0.1700

Data Index: 7882593 (Open Web Text)

Max Activating Token Index: 540

Text #4

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.2858. Min Act: -0.1700

Data Index: 5074201 (Open Web Text)

Max Activating Token Index: 137

Text #5

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.2005. Min Act: -0.1700

Data Index: 4725077 (Open Web Text)

Max Activating Token Index: 981

Text #6

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.2468. Min Act: -0.1700

Data Index: 7362734 (Open Web Text)

Max Activating Token Index: 997

Text #7

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.2366. Min Act: -0.1700

Data Index: 5285224 (Open Web Text)

Max Activating Token Index: 111

Text #8

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.2620. Min Act: -0.1700

Data Index: 3884941 (Open Web Text)

Max Activating Token Index: 240

Text #9

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.2713. Min Act: -0.1700

Data Index: 2286562 (Open Web Text)

Max Activating Token Index: 218

Text #10

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.2124. Min Act: -0.1700

Data Index: 3411688 (Open Web Text)

Max Activating Token Index: 138

Text #11

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.1886. Min Act: -0.1700

Data Index: 3175577 (Open Web Text)

Max Activating Token Index: 943

Text #12

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.2366. Min Act: -0.1700

Data Index: 3576473 (Open Web Text)

Max Activating Token Index: 755

Text #13

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.1934. Min Act: -0.1700

Data Index: 4950436 (Open Web Text)

Max Activating Token Index: 933

Text #14

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.1483. Min Act: -0.1700

Data Index: 3691213 (Open Web Text)

Max Activating Token Index: 268

Text #15

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.1995. Min Act: -0.1700

Data Index: 7478050 (Open Web Text)

Max Activating Token Index: 283

Text #16

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.1486. Min Act: -0.1700

Data Index: 7368402 (Open Web Text)

Max Activating Token Index: 599

Text #17

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.1787. Min Act: -0.1700

Data Index: 4794525 (Open Web Text)

Max Activating Token Index: 210

Text #18

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.1594. Min Act: -0.1700

Data Index: 270408 (Open Web Text)

Max Activating Token Index: 886

Text #19

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.1491. Min Act: -0.1700

Data Index: 1671919 (Open Web Text)

Max Activating Token Index: 958