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

Dataset: Open Web Text

Neuron 9 in Layer 3

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: 3.8529. Min Range: -3.8529

Max Act: 3.8529. Min Act: -0.1700

Data Index: 5267016 (Open Web Text)

Max Activating Token Index: 367

Text #1

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.7986. Min Act: -0.1700

Data Index: 4211393 (Open Web Text)

Max Activating Token Index: 719

Text #2

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.7599. Min Act: -0.1700

Data Index: 3752460 (Open Web Text)

Max Activating Token Index: 682

Text #3

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.7195. Min Act: -0.1700

Data Index: 3244332 (Open Web Text)

Max Activating Token Index: 41

Text #4

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.6641. Min Act: -0.1700

Data Index: 6586570 (Open Web Text)

Max Activating Token Index: 44

Text #5

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.6447. Min Act: -0.1700

Data Index: 3355672 (Open Web Text)

Max Activating Token Index: 400

Text #6

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.6617. Min Act: -0.1700

Data Index: 7903879 (Open Web Text)

Max Activating Token Index: 507

Text #7

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.6541. Min Act: -0.1700

Data Index: 2254214 (Open Web Text)

Max Activating Token Index: 33

Text #8

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.6503. Min Act: -0.1700

Data Index: 100276 (Open Web Text)

Max Activating Token Index: 857

Text #9

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.6351. Min Act: -0.1700

Data Index: 4915574 (Open Web Text)

Max Activating Token Index: 227

Text #10

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.6332. Min Act: -0.1700

Data Index: 3477992 (Open Web Text)

Max Activating Token Index: 114

Text #11

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.6460. Min Act: -0.1700

Data Index: 4814303 (Open Web Text)

Max Activating Token Index: 167

Text #12

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.6059. Min Act: -0.1700

Data Index: 3097727 (Open Web Text)

Max Activating Token Index: 544

Text #13

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.6365. Min Act: -0.1700

Data Index: 4722921 (Open Web Text)

Max Activating Token Index: 534

Text #14

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.6236. Min Act: -0.1700

Data Index: 4964471 (Open Web Text)

Max Activating Token Index: 322

Text #15

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.6347. Min Act: -0.1700

Data Index: 3913478 (Open Web Text)

Max Activating Token Index: 324

Text #16

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.5882. Min Act: -0.1700

Data Index: 5383900 (Open Web Text)

Max Activating Token Index: 351

Text #17

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.5822. Min Act: -0.1700

Data Index: 5828784 (Open Web Text)

Max Activating Token Index: 311

Text #18

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.5774. Min Act: -0.1700

Data Index: 2580835 (Open Web Text)

Max Activating Token Index: 226

Text #19

Max Range: 3.8529. Min Range: -3.8529

Max Act: 3.5533. Min Act: -0.1700

Data Index: 1398943 (Open Web Text)

Max Activating Token Index: 719