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

Dataset: Open Web Text

Neuron 2475 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: 5.4769. Min Range: -5.4769

Max Act: 5.4769. Min Act: -0.1700

Data Index: 2321501 (Open Web Text)

Max Activating Token Index: 711

Text #1

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.3744. Min Act: -0.1700

Data Index: 3615566 (Open Web Text)

Max Activating Token Index: 894

Text #2

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.3466. Min Act: -0.1700

Data Index: 7082864 (Open Web Text)

Max Activating Token Index: 380

Text #3

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.3845. Min Act: -0.1700

Data Index: 8257443 (Open Web Text)

Max Activating Token Index: 837

Text #4

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.3209. Min Act: -0.1700

Data Index: 5187804 (Open Web Text)

Max Activating Token Index: 92

Text #5

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.3176. Min Act: -0.1700

Data Index: 5260846 (Open Web Text)

Max Activating Token Index: 451

Text #6

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.3324. Min Act: -0.1700

Data Index: 6805446 (Open Web Text)

Max Activating Token Index: 475

Text #7

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.3394. Min Act: -0.1700

Data Index: 8442297 (Open Web Text)

Max Activating Token Index: 861

Text #8

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.2904. Min Act: -0.1700

Data Index: 3722136 (Open Web Text)

Max Activating Token Index: 943

Text #9

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.2815. Min Act: -0.1700

Data Index: 3372382 (Open Web Text)

Max Activating Token Index: 279

Text #10

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.2645. Min Act: -0.1700

Data Index: 2327367 (Open Web Text)

Max Activating Token Index: 538

Text #11

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.2517. Min Act: -0.1700

Data Index: 6741606 (Open Web Text)

Max Activating Token Index: 362

Text #12

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.2497. Min Act: -0.1700

Data Index: 5522170 (Open Web Text)

Max Activating Token Index: 407

Text #13

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.2530. Min Act: -0.1700

Data Index: 3999553 (Open Web Text)

Max Activating Token Index: 355

Text #14

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.2831. Min Act: -0.1700

Data Index: 2657247 (Open Web Text)

Max Activating Token Index: 936

Text #15

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.2795. Min Act: -0.1700

Data Index: 4693456 (Open Web Text)

Max Activating Token Index: 355

Text #16

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.2313. Min Act: -0.1700

Data Index: 3336129 (Open Web Text)

Max Activating Token Index: 759

Text #17

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.2067. Min Act: -0.1700

Data Index: 2204770 (Open Web Text)

Max Activating Token Index: 617

Text #18

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.2165. Min Act: -0.1700

Data Index: 2591246 (Open Web Text)

Max Activating Token Index: 685

Text #19

Max Range: 5.4769. Min Range: -5.4769

Max Act: 5.2311. Min Act: -0.1700

Data Index: 96385 (Open Web Text)

Max Activating Token Index: 886