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

Dataset: Open Web Text

Neuron 2392 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: 3.9059. Min Range: -3.9059

Max Act: 3.8846. Min Act: -0.1700

Data Index: 3483514 (Open Web Text)

Max Activating Token Index: 123

Text #1

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.8805. Min Act: -0.1700

Data Index: 6772349 (Open Web Text)

Max Activating Token Index: 860

Text #2

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.9059. Min Act: -0.1700

Data Index: 7011845 (Open Web Text)

Max Activating Token Index: 228

Text #3

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.8331. Min Act: -0.1700

Data Index: 1760493 (Open Web Text)

Max Activating Token Index: 935

Text #4

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.8966. Min Act: -0.1700

Data Index: 4586660 (Open Web Text)

Max Activating Token Index: 418

Text #5

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.8399. Min Act: -0.1700

Data Index: 6172123 (Open Web Text)

Max Activating Token Index: 102

Text #6

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.7955. Min Act: -0.1700

Data Index: 3259305 (Open Web Text)

Max Activating Token Index: 321

Text #7

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.7962. Min Act: -0.1700

Data Index: 3036379 (Open Web Text)

Max Activating Token Index: 638

Text #8

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.7983. Min Act: -0.1700

Data Index: 4701345 (Open Web Text)

Max Activating Token Index: 813

Text #9

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.8088. Min Act: -0.1700

Data Index: 6424594 (Open Web Text)

Max Activating Token Index: 1018

Text #10

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.7678. Min Act: -0.1700

Data Index: 4575680 (Open Web Text)

Max Activating Token Index: 156

Text #11

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.7669. Min Act: -0.1700

Data Index: 1386897 (Open Web Text)

Max Activating Token Index: 618

Text #12

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.7854. Min Act: -0.1700

Data Index: 2549769 (Open Web Text)

Max Activating Token Index: 857

Text #13

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.7587. Min Act: -0.1700

Data Index: 2828546 (Open Web Text)

Max Activating Token Index: 745

Text #14

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.7568. Min Act: -0.1700

Data Index: 2529088 (Open Web Text)

Max Activating Token Index: 280

Text #15

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.7887. Min Act: -0.1700

Data Index: 5473230 (Open Web Text)

Max Activating Token Index: 260

Text #16

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.7573. Min Act: -0.1700

Data Index: 922127 (Open Web Text)

Max Activating Token Index: 812

Text #17

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.7594. Min Act: -0.1700

Data Index: 5783257 (Open Web Text)

Max Activating Token Index: 517

Text #18

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.7701. Min Act: -0.1700

Data Index: 329589 (Open Web Text)

Max Activating Token Index: 422

Text #19

Max Range: 3.9059. Min Range: -3.9059

Max Act: 3.7879. Min Act: -0.1700

Data Index: 292340 (Open Web Text)

Max Activating Token Index: 128