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

Dataset: Open Web Text

Neuron 224 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: 3.9622. Min Range: -3.9622

Max Act: 3.9622. Min Act: -0.1700

Data Index: 4282094 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.9108. Min Act: -0.1700

Data Index: 1965832 (Open Web Text)

Max Activating Token Index: 329

Text #2

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.9237. Min Act: -0.1700

Data Index: 7255334 (Open Web Text)

Max Activating Token Index: 940

Text #3

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.8918. Min Act: -0.1700

Data Index: 5728790 (Open Web Text)

Max Activating Token Index: 559

Text #4

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.8222. Min Act: -0.1700

Data Index: 3790666 (Open Web Text)

Max Activating Token Index: 300

Text #5

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.8316. Min Act: -0.1700

Data Index: 8095881 (Open Web Text)

Max Activating Token Index: 334

Text #6

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.8282. Min Act: -0.1700

Data Index: 3823944 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.8277. Min Act: -0.1700

Data Index: 8223049 (Open Web Text)

Max Activating Token Index: 878

Text #8

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.8016. Min Act: -0.1700

Data Index: 5352300 (Open Web Text)

Max Activating Token Index: 929

Text #9

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.7674. Min Act: -0.1700

Data Index: 5232058 (Open Web Text)

Max Activating Token Index: 688

Text #10

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.7832. Min Act: -0.1700

Data Index: 5187980 (Open Web Text)

Max Activating Token Index: 250

Text #11

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.7538. Min Act: -0.1700

Data Index: 1725705 (Open Web Text)

Max Activating Token Index: 446

Text #12

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.7903. Min Act: -0.1700

Data Index: 8367023 (Open Web Text)

Max Activating Token Index: 824

Text #13

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.7631. Min Act: -0.1700

Data Index: 3044849 (Open Web Text)

Max Activating Token Index: 653

Text #14

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.7702. Min Act: -0.1700

Data Index: 584238 (Open Web Text)

Max Activating Token Index: 746

Text #15

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.7318. Min Act: -0.1700

Data Index: 4117102 (Open Web Text)

Max Activating Token Index: 330

Text #16

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.7231. Min Act: -0.1700

Data Index: 5119167 (Open Web Text)

Max Activating Token Index: 309

Text #17

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.6954. Min Act: -0.1700

Data Index: 2039687 (Open Web Text)

Max Activating Token Index: 737

Text #18

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.7177. Min Act: -0.1700

Data Index: 4185153 (Open Web Text)

Max Activating Token Index: 1021

Text #19

Max Range: 3.9622. Min Range: -3.9622

Max Act: 3.7160. Min Act: -0.1700

Data Index: 3935426 (Open Web Text)

Max Activating Token Index: 318