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

Dataset: Open Web Text

Neuron 1859 in Layer 2

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: 1.6324. Min Range: -1.6324

Max Act: 1.6324. Min Act: -0.1700

Data Index: 1547242 (Open Web Text)

Max Activating Token Index: 226

Text #1

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5777. Min Act: -0.1697

Data Index: 4301514 (Open Web Text)

Max Activating Token Index: 398

Text #2

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5747. Min Act: -0.1700

Data Index: 4301507 (Open Web Text)

Max Activating Token Index: 32

Text #3

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5570. Min Act: -0.1700

Data Index: 1094717 (Open Web Text)

Max Activating Token Index: 734

Text #4

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5610. Min Act: -0.1700

Data Index: 7218967 (Open Web Text)

Max Activating Token Index: 578

Text #5

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5630. Min Act: -0.1700

Data Index: 7218969 (Open Web Text)

Max Activating Token Index: 452

Text #6

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5492. Min Act: -0.1700

Data Index: 2044685 (Open Web Text)

Max Activating Token Index: 428

Text #7

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5523. Min Act: -0.1700

Data Index: 2505091 (Open Web Text)

Max Activating Token Index: 464

Text #8

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5526. Min Act: -0.1700

Data Index: 4527829 (Open Web Text)

Max Activating Token Index: 539

Text #9

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5354. Min Act: -0.1699

Data Index: 8219968 (Open Web Text)

Max Activating Token Index: 924

Text #10

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5428. Min Act: -0.1700

Data Index: 6679245 (Open Web Text)

Max Activating Token Index: 203

Text #11

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5288. Min Act: -0.1700

Data Index: 4235219 (Open Web Text)

Max Activating Token Index: 889

Text #12

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5446. Min Act: -0.1700

Data Index: 2057172 (Open Web Text)

Max Activating Token Index: 478

Text #13

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5255. Min Act: -0.1700

Data Index: 3178221 (Open Web Text)

Max Activating Token Index: 780

Text #14

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5198. Min Act: -0.1700

Data Index: 3944141 (Open Web Text)

Max Activating Token Index: 578

Text #15

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5163. Min Act: -0.1699

Data Index: 8375887 (Open Web Text)

Max Activating Token Index: 502

Text #16

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5167. Min Act: -0.1700

Data Index: 7336753 (Open Web Text)

Max Activating Token Index: 382

Text #17

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5134. Min Act: -0.1700

Data Index: 5276788 (Open Web Text)

Max Activating Token Index: 56

Text #18

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5011. Min Act: -0.1700

Data Index: 2886472 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 1.6324. Min Range: -1.6324

Max Act: 1.5042. Min Act: -0.1696

Data Index: 7631511 (Open Web Text)

Max Activating Token Index: 337