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

Dataset: Open Web Text

Neuron 23 in Layer 6

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: 5.6717. Min Range: -5.6717

Max Act: 5.6562. Min Act: -0.1700

Data Index: 7541311 (Open Web Text)

Max Activating Token Index: 791

Text #1

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.6717. Min Act: -0.1700

Data Index: 2503764 (Open Web Text)

Max Activating Token Index: 265

Text #2

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.6397. Min Act: -0.1700

Data Index: 728735 (Open Web Text)

Max Activating Token Index: 944

Text #3

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.6315. Min Act: -0.1700

Data Index: 7389818 (Open Web Text)

Max Activating Token Index: 1017

Text #4

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.6285. Min Act: -0.1700

Data Index: 1572723 (Open Web Text)

Max Activating Token Index: 417

Text #5

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.6289. Min Act: -0.1700

Data Index: 7491953 (Open Web Text)

Max Activating Token Index: 825

Text #6

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.6396. Min Act: -0.1700

Data Index: 7566139 (Open Web Text)

Max Activating Token Index: 589

Text #7

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.6351. Min Act: -0.1700

Data Index: 347752 (Open Web Text)

Max Activating Token Index: 602

Text #8

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.6145. Min Act: -0.1700

Data Index: 2217184 (Open Web Text)

Max Activating Token Index: 779

Text #9

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.6215. Min Act: -0.1700

Data Index: 6217458 (Open Web Text)

Max Activating Token Index: 711

Text #10

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.5444. Min Act: -0.1700

Data Index: 1142328 (Open Web Text)

Max Activating Token Index: 879

Text #11

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.5868. Min Act: -0.1700

Data Index: 2665582 (Open Web Text)

Max Activating Token Index: 423

Text #12

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.5937. Min Act: -0.1700

Data Index: 6754993 (Open Web Text)

Max Activating Token Index: 428

Text #13

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.5323. Min Act: -0.1700

Data Index: 939716 (Open Web Text)

Max Activating Token Index: 115

Text #14

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.5882. Min Act: -0.1700

Data Index: 2804033 (Open Web Text)

Max Activating Token Index: 745

Text #15

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.5303. Min Act: -0.1700

Data Index: 4668418 (Open Web Text)

Max Activating Token Index: 358

Text #16

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.5367. Min Act: -0.1700

Data Index: 3049391 (Open Web Text)

Max Activating Token Index: 648

Text #17

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.5360. Min Act: -0.1700

Data Index: 3207967 (Open Web Text)

Max Activating Token Index: 914

Text #18

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.5125. Min Act: -0.1700

Data Index: 4821514 (Open Web Text)

Max Activating Token Index: 959

Text #19

Max Range: 5.6717. Min Range: -5.6717

Max Act: 5.5543. Min Act: -0.1700

Data Index: 2730786 (Open Web Text)

Max Activating Token Index: 917