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

Dataset: Open Web Text

Neuron 2379 in Layer 3

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: 3.3859. Min Range: -3.3859

Max Act: 3.3859. Min Act: -0.1700

Data Index: 3434556 (Open Web Text)

Max Activating Token Index: 616

Text #1

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.3245. Min Act: -0.1700

Data Index: 5076514 (Open Web Text)

Max Activating Token Index: 743

Text #2

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2976. Min Act: -0.1700

Data Index: 1285210 (Open Web Text)

Max Activating Token Index: 837

Text #3

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.3325. Min Act: -0.1700

Data Index: 3805949 (Open Web Text)

Max Activating Token Index: 971

Text #4

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2247. Min Act: -0.1700

Data Index: 5404502 (Open Web Text)

Max Activating Token Index: 592

Text #5

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.3097. Min Act: -0.1696

Data Index: 2643413 (Open Web Text)

Max Activating Token Index: 946

Text #6

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2953. Min Act: -0.1700

Data Index: 8043720 (Open Web Text)

Max Activating Token Index: 479

Text #7

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2660. Min Act: -0.1700

Data Index: 921654 (Open Web Text)

Max Activating Token Index: 929

Text #8

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2410. Min Act: -0.1700

Data Index: 3120286 (Open Web Text)

Max Activating Token Index: 517

Text #9

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2399. Min Act: -0.1700

Data Index: 2302921 (Open Web Text)

Max Activating Token Index: 838

Text #10

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2655. Min Act: -0.1698

Data Index: 754422 (Open Web Text)

Max Activating Token Index: 618

Text #11

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2614. Min Act: -0.1691

Data Index: 1117812 (Open Web Text)

Max Activating Token Index: 817

Text #12

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2515. Min Act: -0.1700

Data Index: 4937321 (Open Web Text)

Max Activating Token Index: 305

Text #13

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2141. Min Act: -0.1700

Data Index: 8519878 (Open Web Text)

Max Activating Token Index: 519

Text #14

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2577. Min Act: -0.1700

Data Index: 5076522 (Open Web Text)

Max Activating Token Index: 971

Text #15

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2492. Min Act: -0.1700

Data Index: 3559703 (Open Web Text)

Max Activating Token Index: 344

Text #16

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2455. Min Act: -0.1700

Data Index: 1117815 (Open Web Text)

Max Activating Token Index: 806

Text #17

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2477. Min Act: -0.1700

Data Index: 4560883 (Open Web Text)

Max Activating Token Index: 383

Text #18

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2416. Min Act: -0.1700

Data Index: 5286876 (Open Web Text)

Max Activating Token Index: 57

Text #19

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.1962. Min Act: -0.1700

Data Index: 1017758 (Open Web Text)

Max Activating Token Index: 263