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

Dataset: Open Web Text

Neuron 2696 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: 3.0115. Min Range: -3.0115

Max Act: 3.0115. Min Act: -0.1700

Data Index: 7791322 (Open Web Text)

Max Activating Token Index: 31

Text #1

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9761. Min Act: -0.1700

Data Index: 2408022 (Open Web Text)

Max Activating Token Index: 1021

Text #2

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9631. Min Act: -0.1700

Data Index: 2255463 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9742. Min Act: -0.1700

Data Index: 2981357 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9543. Min Act: -0.1700

Data Index: 8636281 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9520. Min Act: -0.1700

Data Index: 3745079 (Open Web Text)

Max Activating Token Index: 389

Text #6

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9096. Min Act: -0.1700

Data Index: 2536359 (Open Web Text)

Max Activating Token Index: 892

Text #7

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9392. Min Act: -0.1700

Data Index: 3804174 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9577. Min Act: -0.1700

Data Index: 7223810 (Open Web Text)

Max Activating Token Index: 528

Text #9

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9594. Min Act: -0.1700

Data Index: 7193024 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9205. Min Act: -0.1700

Data Index: 7815590 (Open Web Text)

Max Activating Token Index: 1020

Text #11

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9229. Min Act: -0.1700

Data Index: 914228 (Open Web Text)

Max Activating Token Index: 994

Text #12

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9241. Min Act: -0.1700

Data Index: 1063965 (Open Web Text)

Max Activating Token Index: 234

Text #13

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9358. Min Act: -0.1700

Data Index: 4112957 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9190. Min Act: -0.1700

Data Index: 2171022 (Open Web Text)

Max Activating Token Index: 311

Text #15

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9165. Min Act: -0.1700

Data Index: 5145004 (Open Web Text)

Max Activating Token Index: 34

Text #16

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.8750. Min Act: -0.1700

Data Index: 5726473 (Open Web Text)

Max Activating Token Index: 1013

Text #17

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9112. Min Act: -0.1700

Data Index: 399773 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9032. Min Act: -0.1700

Data Index: 3897810 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 3.0115. Min Range: -3.0115

Max Act: 2.9019. Min Act: -0.1700

Data Index: 6261952 (Open Web Text)

Max Activating Token Index: 18