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

Dataset: Open Web Text

Neuron 1616 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: 1.8193. Min Range: -1.8193

Max Act: 1.8193. Min Act: -0.1700

Data Index: 6479954 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7838. Min Act: -0.1700

Data Index: 2268990 (Open Web Text)

Max Activating Token Index: 364

Text #2

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.8000. Min Act: -0.1700

Data Index: 8056091 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7562. Min Act: -0.1700

Data Index: 4047306 (Open Web Text)

Max Activating Token Index: 912

Text #4

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7826. Min Act: -0.1700

Data Index: 3877815 (Open Web Text)

Max Activating Token Index: 815

Text #5

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7560. Min Act: -0.1700

Data Index: 8286953 (Open Web Text)

Max Activating Token Index: 421

Text #6

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7723. Min Act: -0.1700

Data Index: 8480194 (Open Web Text)

Max Activating Token Index: 477

Text #7

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7430. Min Act: -0.1700

Data Index: 5392929 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7451. Min Act: -0.1700

Data Index: 7221810 (Open Web Text)

Max Activating Token Index: 562

Text #9

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7291. Min Act: -0.1700

Data Index: 6827166 (Open Web Text)

Max Activating Token Index: 588

Text #10

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7359. Min Act: -0.1700

Data Index: 2221778 (Open Web Text)

Max Activating Token Index: 259

Text #11

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7530. Min Act: -0.1700

Data Index: 3877166 (Open Web Text)

Max Activating Token Index: 157

Text #12

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7426. Min Act: -0.1700

Data Index: 1163546 (Open Web Text)

Max Activating Token Index: 901

Text #13

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7478. Min Act: -0.1700

Data Index: 3628449 (Open Web Text)

Max Activating Token Index: 806

Text #14

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7447. Min Act: -0.1700

Data Index: 8792776 (Open Web Text)

Max Activating Token Index: 651

Text #15

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7430. Min Act: -0.1700

Data Index: 8392620 (Open Web Text)

Max Activating Token Index: 439

Text #16

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7429. Min Act: -0.1700

Data Index: 2810949 (Open Web Text)

Max Activating Token Index: 856

Text #17

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7289. Min Act: -0.1700

Data Index: 1916510 (Open Web Text)

Max Activating Token Index: 773

Text #18

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7319. Min Act: -0.1700

Data Index: 3496711 (Open Web Text)

Max Activating Token Index: 451

Text #19

Max Range: 1.8193. Min Range: -1.8193

Max Act: 1.7296. Min Act: -0.1700

Data Index: 5028590 (Open Web Text)

Max Activating Token Index: 458