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

Dataset: Open Web Text

Neuron 2932 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: 4.7493. Min Range: -4.7493

Max Act: 4.7255. Min Act: -0.1700

Data Index: 678324 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.7493. Min Act: -0.1700

Data Index: 3498835 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.7076. Min Act: -0.1700

Data Index: 4803357 (Open Web Text)

Max Activating Token Index: 1006

Text #3

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.7024. Min Act: -0.1700

Data Index: 6539914 (Open Web Text)

Max Activating Token Index: 976

Text #4

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.7110. Min Act: -0.1700

Data Index: 6201716 (Open Web Text)

Max Activating Token Index: 578

Text #5

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.6600. Min Act: -0.1700

Data Index: 813953 (Open Web Text)

Max Activating Token Index: 551

Text #6

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.6376. Min Act: -0.1700

Data Index: 7461792 (Open Web Text)

Max Activating Token Index: 521

Text #7

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.7061. Min Act: -0.1700

Data Index: 8733111 (Open Web Text)

Max Activating Token Index: 462

Text #8

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.6343. Min Act: -0.1700

Data Index: 5610977 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.5896. Min Act: -0.1700

Data Index: 2034648 (Open Web Text)

Max Activating Token Index: 1007

Text #10

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.6202. Min Act: -0.1700

Data Index: 2457846 (Open Web Text)

Max Activating Token Index: 356

Text #11

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.6962. Min Act: -0.1700

Data Index: 1671010 (Open Web Text)

Max Activating Token Index: 622

Text #12

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.6419. Min Act: -0.1700

Data Index: 3230338 (Open Web Text)

Max Activating Token Index: 786

Text #13

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.6259. Min Act: -0.1700

Data Index: 3114728 (Open Web Text)

Max Activating Token Index: 815

Text #14

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.6444. Min Act: -0.1700

Data Index: 2555691 (Open Web Text)

Max Activating Token Index: 395

Text #15

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.6384. Min Act: -0.1700

Data Index: 8286089 (Open Web Text)

Max Activating Token Index: 642

Text #16

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.5716. Min Act: -0.1700

Data Index: 1224976 (Open Web Text)

Max Activating Token Index: 414

Text #17

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.6511. Min Act: -0.1700

Data Index: 813265 (Open Web Text)

Max Activating Token Index: 68

Text #18

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.6264. Min Act: -0.1700

Data Index: 37512 (Open Web Text)

Max Activating Token Index: 935

Text #19

Max Range: 4.7493. Min Range: -4.7493

Max Act: 4.6232. Min Act: -0.1700

Data Index: 1650815 (Open Web Text)

Max Activating Token Index: 177