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

Dataset: Open Web Text

Neuron 2080 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: 4.7445. Min Range: -4.7445

Max Act: 4.7445. Min Act: -0.1700

Data Index: 7634293 (Open Web Text)

Max Activating Token Index: 522

Text #1

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.6615. Min Act: -0.1700

Data Index: 3503654 (Open Web Text)

Max Activating Token Index: 251

Text #2

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.6015. Min Act: -0.1700

Data Index: 862583 (Open Web Text)

Max Activating Token Index: 527

Text #3

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.5592. Min Act: -0.1700

Data Index: 2112876 (Open Web Text)

Max Activating Token Index: 723

Text #4

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.5536. Min Act: -0.1700

Data Index: 644038 (Open Web Text)

Max Activating Token Index: 708

Text #5

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.5218. Min Act: -0.1700

Data Index: 5831155 (Open Web Text)

Max Activating Token Index: 137

Text #6

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.5348. Min Act: -0.1700

Data Index: 2602606 (Open Web Text)

Max Activating Token Index: 345

Text #7

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.5130. Min Act: -0.1700

Data Index: 7221913 (Open Web Text)

Max Activating Token Index: 330

Text #8

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.5507. Min Act: -0.1700

Data Index: 1814467 (Open Web Text)

Max Activating Token Index: 87

Text #9

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.5388. Min Act: -0.1700

Data Index: 185711 (Open Web Text)

Max Activating Token Index: 740

Text #10

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.4792. Min Act: -0.1700

Data Index: 6342188 (Open Web Text)

Max Activating Token Index: 198

Text #11

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.4745. Min Act: -0.1700

Data Index: 7417961 (Open Web Text)

Max Activating Token Index: 295

Text #12

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.4626. Min Act: -0.1700

Data Index: 6874583 (Open Web Text)

Max Activating Token Index: 364

Text #13

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.4999. Min Act: -0.1700

Data Index: 6401348 (Open Web Text)

Max Activating Token Index: 224

Text #14

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.4774. Min Act: -0.1700

Data Index: 1848958 (Open Web Text)

Max Activating Token Index: 888

Text #15

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.4894. Min Act: -0.1700

Data Index: 5952388 (Open Web Text)

Max Activating Token Index: 703

Text #16

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.4951. Min Act: -0.1700

Data Index: 1724664 (Open Web Text)

Max Activating Token Index: 840

Text #17

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.4703. Min Act: -0.1700

Data Index: 680651 (Open Web Text)

Max Activating Token Index: 644

Text #18

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.4827. Min Act: -0.1700

Data Index: 2840192 (Open Web Text)

Max Activating Token Index: 263

Text #19

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.5141. Min Act: -0.1700

Data Index: 737121 (Open Web Text)

Max Activating Token Index: 740