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

Dataset: Open Web Text

Neuron 411 in Layer 6

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: 4.6390. Min Range: -4.6390

Max Act: 4.6390. Min Act: -0.1700

Data Index: 2211355 (Open Web Text)

Max Activating Token Index: 65

Text #1

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.6154. Min Act: -0.1700

Data Index: 4494076 (Open Web Text)

Max Activating Token Index: 703

Text #2

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.4666. Min Act: -0.1700

Data Index: 1292694 (Open Web Text)

Max Activating Token Index: 156

Text #3

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.4660. Min Act: -0.1700

Data Index: 6760919 (Open Web Text)

Max Activating Token Index: 678

Text #4

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.4447. Min Act: -0.1700

Data Index: 5876331 (Open Web Text)

Max Activating Token Index: 1003

Text #5

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.4680. Min Act: -0.1700

Data Index: 6201597 (Open Web Text)

Max Activating Token Index: 653

Text #6

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.4547. Min Act: -0.1700

Data Index: 2481452 (Open Web Text)

Max Activating Token Index: 307

Text #7

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.4179. Min Act: -0.1700

Data Index: 4920964 (Open Web Text)

Max Activating Token Index: 290

Text #8

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.4702. Min Act: -0.1700

Data Index: 7942303 (Open Web Text)

Max Activating Token Index: 1012

Text #9

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.4234. Min Act: -0.1700

Data Index: 2182460 (Open Web Text)

Max Activating Token Index: 844

Text #10

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.4418. Min Act: -0.1700

Data Index: 6704525 (Open Web Text)

Max Activating Token Index: 782

Text #11

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.4159. Min Act: -0.1700

Data Index: 6365666 (Open Web Text)

Max Activating Token Index: 746

Text #12

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.4403. Min Act: -0.1700

Data Index: 4433882 (Open Web Text)

Max Activating Token Index: 224

Text #13

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.4311. Min Act: -0.1700

Data Index: 3931220 (Open Web Text)

Max Activating Token Index: 255

Text #14

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.4223. Min Act: -0.1700

Data Index: 122528 (Open Web Text)

Max Activating Token Index: 693

Text #15

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.4057. Min Act: -0.1700

Data Index: 1967075 (Open Web Text)

Max Activating Token Index: 167

Text #16

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.4436. Min Act: -0.1700

Data Index: 4920962 (Open Web Text)

Max Activating Token Index: 1020

Text #17

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.3872. Min Act: -0.1700

Data Index: 5912533 (Open Web Text)

Max Activating Token Index: 122

Text #18

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.3792. Min Act: -0.1700

Data Index: 7844946 (Open Web Text)

Max Activating Token Index: 341

Text #19

Max Range: 4.6390. Min Range: -4.6390

Max Act: 4.3733. Min Act: -0.1700

Data Index: 2829676 (Open Web Text)

Max Activating Token Index: 770