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

Dataset: Open Web Text

Neuron 233 in Layer 4

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: 3.1548. Min Range: -3.1548

Max Act: 3.1548. Min Act: -0.1700

Data Index: 3030106 (Open Web Text)

Max Activating Token Index: 350

Text #1

Max Range: 3.1548. Min Range: -3.1548

Max Act: 3.1250. Min Act: -0.1700

Data Index: 6034930 (Open Web Text)

Max Activating Token Index: 319

Text #2

Max Range: 3.1548. Min Range: -3.1548

Max Act: 3.0865. Min Act: -0.1700

Data Index: 425414 (Open Web Text)

Max Activating Token Index: 494

Text #3

Max Range: 3.1548. Min Range: -3.1548

Max Act: 3.0888. Min Act: -0.1700

Data Index: 5596306 (Open Web Text)

Max Activating Token Index: 157

Text #4

Max Range: 3.1548. Min Range: -3.1548

Max Act: 3.0786. Min Act: -0.1700

Data Index: 6273101 (Open Web Text)

Max Activating Token Index: 108

Text #5

Max Range: 3.1548. Min Range: -3.1548

Max Act: 3.0592. Min Act: -0.1700

Data Index: 5418703 (Open Web Text)

Max Activating Token Index: 782

Text #6

Max Range: 3.1548. Min Range: -3.1548

Max Act: 3.0673. Min Act: -0.1700

Data Index: 4534617 (Open Web Text)

Max Activating Token Index: 856

Text #7

Max Range: 3.1548. Min Range: -3.1548

Max Act: 3.0678. Min Act: -0.1700

Data Index: 715264 (Open Web Text)

Max Activating Token Index: 427

Text #8

Max Range: 3.1548. Min Range: -3.1548

Max Act: 3.0280. Min Act: -0.1700

Data Index: 7864714 (Open Web Text)

Max Activating Token Index: 188

Text #9

Max Range: 3.1548. Min Range: -3.1548

Max Act: 3.0124. Min Act: -0.1700

Data Index: 6271597 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 3.1548. Min Range: -3.1548

Max Act: 3.0107. Min Act: -0.1700

Data Index: 6547332 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 3.1548. Min Range: -3.1548

Max Act: 3.0457. Min Act: -0.1700

Data Index: 8574253 (Open Web Text)

Max Activating Token Index: 603

Text #12

Max Range: 3.1548. Min Range: -3.1548

Max Act: 2.9810. Min Act: -0.1700

Data Index: 6877717 (Open Web Text)

Max Activating Token Index: 354

Text #13

Max Range: 3.1548. Min Range: -3.1548

Max Act: 3.0093. Min Act: -0.1700

Data Index: 7363811 (Open Web Text)

Max Activating Token Index: 751

Text #14

Max Range: 3.1548. Min Range: -3.1548

Max Act: 2.9845. Min Act: -0.1700

Data Index: 7515904 (Open Web Text)

Max Activating Token Index: 605

Text #15

Max Range: 3.1548. Min Range: -3.1548

Max Act: 2.9887. Min Act: -0.1700

Data Index: 340889 (Open Web Text)

Max Activating Token Index: 995

Text #16

Max Range: 3.1548. Min Range: -3.1548

Max Act: 2.9912. Min Act: -0.1700

Data Index: 1030737 (Open Web Text)

Max Activating Token Index: 247

Text #17

Max Range: 3.1548. Min Range: -3.1548

Max Act: 2.9569. Min Act: -0.1700

Data Index: 1257235 (Open Web Text)

Max Activating Token Index: 441

Text #18

Max Range: 3.1548. Min Range: -3.1548

Max Act: 2.9682. Min Act: -0.1700

Data Index: 5455505 (Open Web Text)

Max Activating Token Index: 987

Text #19

Max Range: 3.1548. Min Range: -3.1548

Max Act: 2.9512. Min Act: -0.1700

Data Index: 2684542 (Open Web Text)

Max Activating Token Index: 173