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

Dataset: Open Web Text

Neuron 2637 in Layer 5

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: 3.1806. Min Range: -3.1806

Max Act: 3.1806. Min Act: -0.1700

Data Index: 3370149 (Open Web Text)

Max Activating Token Index: 766

Text #1

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.1685. Min Act: -0.1700

Data Index: 6333723 (Open Web Text)

Max Activating Token Index: 687

Text #2

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0883. Min Act: -0.1700

Data Index: 2484348 (Open Web Text)

Max Activating Token Index: 460

Text #3

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0877. Min Act: -0.1700

Data Index: 7103019 (Open Web Text)

Max Activating Token Index: 386

Text #4

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0748. Min Act: -0.1700

Data Index: 85533 (Open Web Text)

Max Activating Token Index: 561

Text #5

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0636. Min Act: -0.1700

Data Index: 7324288 (Open Web Text)

Max Activating Token Index: 140

Text #6

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0340. Min Act: -0.1700

Data Index: 7815015 (Open Web Text)

Max Activating Token Index: 542

Text #7

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0443. Min Act: -0.1700

Data Index: 4846230 (Open Web Text)

Max Activating Token Index: 237

Text #8

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0177. Min Act: -0.1700

Data Index: 4333444 (Open Web Text)

Max Activating Token Index: 718

Text #9

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0170. Min Act: -0.1700

Data Index: 13558 (Open Web Text)

Max Activating Token Index: 797

Text #10

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0410. Min Act: -0.1700

Data Index: 5171683 (Open Web Text)

Max Activating Token Index: 197

Text #11

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0116. Min Act: -0.1700

Data Index: 8598874 (Open Web Text)

Max Activating Token Index: 440

Text #12

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0198. Min Act: -0.1700

Data Index: 5717367 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0382. Min Act: -0.1700

Data Index: 7148034 (Open Web Text)

Max Activating Token Index: 155

Text #14

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0069. Min Act: -0.1700

Data Index: 7665871 (Open Web Text)

Max Activating Token Index: 462

Text #15

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0074. Min Act: -0.1700

Data Index: 3251716 (Open Web Text)

Max Activating Token Index: 709

Text #16

Max Range: 3.1806. Min Range: -3.1806

Max Act: 3.0068. Min Act: -0.1700

Data Index: 7403613 (Open Web Text)

Max Activating Token Index: 446

Text #17

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9831. Min Act: -0.1700

Data Index: 6017924 (Open Web Text)

Max Activating Token Index: 672

Text #18

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9680. Min Act: -0.1700

Data Index: 5944737 (Open Web Text)

Max Activating Token Index: 392

Text #19

Max Range: 3.1806. Min Range: -3.1806

Max Act: 2.9795. Min Act: -0.1700

Data Index: 1655450 (Open Web Text)

Max Activating Token Index: 377