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

Dataset: Open Web Text

Neuron 1240 in Layer 1

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: 1.6976. Min Range: -1.6976

Max Act: 1.6841. Min Act: -0.1700

Data Index: 7447581 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6976. Min Act: -0.1700

Data Index: 179722 (Open Web Text)

Max Activating Token Index: 684

Text #2

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6797. Min Act: -0.1700

Data Index: 8673251 (Open Web Text)

Max Activating Token Index: 336

Text #3

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6869. Min Act: -0.1700

Data Index: 1507806 (Open Web Text)

Max Activating Token Index: 140

Text #4

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6716. Min Act: -0.1700

Data Index: 6177157 (Open Web Text)

Max Activating Token Index: 336

Text #5

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6870. Min Act: -0.1700

Data Index: 999515 (Open Web Text)

Max Activating Token Index: 984

Text #6

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6503. Min Act: -0.1700

Data Index: 7937729 (Open Web Text)

Max Activating Token Index: 26

Text #7

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6704. Min Act: -0.1700

Data Index: 7601935 (Open Web Text)

Max Activating Token Index: 770

Text #8

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6681. Min Act: -0.1700

Data Index: 7416118 (Open Web Text)

Max Activating Token Index: 600

Text #9

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6699. Min Act: -0.1700

Data Index: 4830631 (Open Web Text)

Max Activating Token Index: 66

Text #10

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6516. Min Act: -0.1700

Data Index: 5800069 (Open Web Text)

Max Activating Token Index: 573

Text #11

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6458. Min Act: -0.1700

Data Index: 1588593 (Open Web Text)

Max Activating Token Index: 565

Text #12

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6299. Min Act: -0.1700

Data Index: 7225480 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6305. Min Act: -0.1700

Data Index: 1827019 (Open Web Text)

Max Activating Token Index: 539

Text #14

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6527. Min Act: -0.1700

Data Index: 2026804 (Open Web Text)

Max Activating Token Index: 541

Text #15

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6467. Min Act: -0.1700

Data Index: 523733 (Open Web Text)

Max Activating Token Index: 882

Text #16

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6373. Min Act: -0.1700

Data Index: 4883271 (Open Web Text)

Max Activating Token Index: 638

Text #17

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6367. Min Act: -0.1700

Data Index: 3203141 (Open Web Text)

Max Activating Token Index: 750

Text #18

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6286. Min Act: -0.1700

Data Index: 361456 (Open Web Text)

Max Activating Token Index: 36

Text #19

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6343. Min Act: -0.1700

Data Index: 4788918 (Open Web Text)

Max Activating Token Index: 286