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

Dataset: Open Web Text

Neuron 1086 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: 4.8637. Min Range: -4.8637

Max Act: 4.8637. Min Act: -0.1700

Data Index: 8676253 (Open Web Text)

Max Activating Token Index: 372

Text #1

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.7545. Min Act: -0.1700

Data Index: 6839167 (Open Web Text)

Max Activating Token Index: 43

Text #2

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.7169. Min Act: -0.1700

Data Index: 3691458 (Open Web Text)

Max Activating Token Index: 21

Text #3

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.7215. Min Act: -0.1700

Data Index: 6706388 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.6987. Min Act: -0.1700

Data Index: 1852352 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.6837. Min Act: -0.1700

Data Index: 2141446 (Open Web Text)

Max Activating Token Index: 287

Text #6

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.6267. Min Act: -0.1700

Data Index: 4686417 (Open Web Text)

Max Activating Token Index: 186

Text #7

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.6336. Min Act: -0.1700

Data Index: 5075753 (Open Web Text)

Max Activating Token Index: 415

Text #8

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.6074. Min Act: -0.1700

Data Index: 2935902 (Open Web Text)

Max Activating Token Index: 31

Text #9

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.6021. Min Act: -0.1700

Data Index: 8559818 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.6006. Min Act: -0.1700

Data Index: 1434183 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.5718. Min Act: -0.1700

Data Index: 7576307 (Open Web Text)

Max Activating Token Index: 22

Text #12

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.5713. Min Act: -0.1700

Data Index: 5891399 (Open Web Text)

Max Activating Token Index: 188

Text #13

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.5728. Min Act: -0.1700

Data Index: 7868492 (Open Web Text)

Max Activating Token Index: 178

Text #14

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.5647. Min Act: -0.1700

Data Index: 8425310 (Open Web Text)

Max Activating Token Index: 413

Text #15

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.5624. Min Act: -0.1700

Data Index: 1004254 (Open Web Text)

Max Activating Token Index: 36

Text #16

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.5712. Min Act: -0.1700

Data Index: 3467086 (Open Web Text)

Max Activating Token Index: 58

Text #17

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.5951. Min Act: -0.1700

Data Index: 77943 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.5883. Min Act: -0.1700

Data Index: 4289383 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.8637. Min Range: -4.8637

Max Act: 4.5652. Min Act: -0.1700

Data Index: 383761 (Open Web Text)

Max Activating Token Index: 201