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

Dataset: Open Web Text

Neuron 2704 in Layer 1

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: 1.5724. Min Range: -1.5724

Max Act: 1.5724. Min Act: -0.1700

Data Index: 1095952 (Open Web Text)

Max Activating Token Index: 379

Text #1

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.5293. Min Act: -0.1700

Data Index: 2354087 (Open Web Text)

Max Activating Token Index: 266

Text #2

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4920. Min Act: -0.1700

Data Index: 6366411 (Open Web Text)

Max Activating Token Index: 98

Text #3

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4878. Min Act: -0.1700

Data Index: 8576525 (Open Web Text)

Max Activating Token Index: 308

Text #4

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4808. Min Act: -0.1700

Data Index: 7082223 (Open Web Text)

Max Activating Token Index: 251

Text #5

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4742. Min Act: -0.1700

Data Index: 8284098 (Open Web Text)

Max Activating Token Index: 22

Text #6

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4683. Min Act: -0.1700

Data Index: 2126241 (Open Web Text)

Max Activating Token Index: 554

Text #7

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4646. Min Act: -0.1700

Data Index: 3158185 (Open Web Text)

Max Activating Token Index: 158

Text #8

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4578. Min Act: -0.1700

Data Index: 2803325 (Open Web Text)

Max Activating Token Index: 482

Text #9

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4586. Min Act: -0.1700

Data Index: 5559945 (Open Web Text)

Max Activating Token Index: 44

Text #10

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4633. Min Act: -0.1698

Data Index: 3158184 (Open Web Text)

Max Activating Token Index: 617

Text #11

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4468. Min Act: -0.1700

Data Index: 5850441 (Open Web Text)

Max Activating Token Index: 228

Text #12

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4477. Min Act: -0.1700

Data Index: 2460195 (Open Web Text)

Max Activating Token Index: 677

Text #13

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4394. Min Act: -0.1700

Data Index: 1331072 (Open Web Text)

Max Activating Token Index: 155

Text #14

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4380. Min Act: -0.1700

Data Index: 2155809 (Open Web Text)

Max Activating Token Index: 119

Text #15

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4365. Min Act: -0.1700

Data Index: 5597821 (Open Web Text)

Max Activating Token Index: 713

Text #16

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4506. Min Act: -0.1700

Data Index: 5989100 (Open Web Text)

Max Activating Token Index: 539

Text #17

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4380. Min Act: -0.1700

Data Index: 7988685 (Open Web Text)

Max Activating Token Index: 556

Text #18

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4450. Min Act: -0.1700

Data Index: 2065208 (Open Web Text)

Max Activating Token Index: 64

Text #19

Max Range: 1.5724. Min Range: -1.5724

Max Act: 1.4363. Min Act: -0.1700

Data Index: 5594218 (Open Web Text)

Max Activating Token Index: 388