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

Dataset: Open Web Text

Neuron 623 in Layer 0

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: 1.4462. Min Range: -1.4462

Max Act: 1.4392. Min Act: -0.1626

Data Index: 8821174 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4403. Min Act: -0.1606

Data Index: 4277539 (Open Web Text)

Max Activating Token Index: 25

Text #2

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4417. Min Act: -0.1687

Data Index: 6116924 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4436. Min Act: -0.1351

Data Index: 4659644 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4462. Min Act: -0.1516

Data Index: 5419129 (Open Web Text)

Max Activating Token Index: 26

Text #5

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4244. Min Act: -0.1561

Data Index: 3341633 (Open Web Text)

Max Activating Token Index: 25

Text #6

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4278. Min Act: -0.1673

Data Index: 8741019 (Open Web Text)

Max Activating Token Index: 27

Text #7

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4288. Min Act: -0.1681

Data Index: 4815306 (Open Web Text)

Max Activating Token Index: 31

Text #8

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4215. Min Act: -0.1580

Data Index: 4815298 (Open Web Text)

Max Activating Token Index: 28

Text #9

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4202. Min Act: -0.1677

Data Index: 3243098 (Open Web Text)

Max Activating Token Index: 21

Text #10

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4231. Min Act: -0.1462

Data Index: 3051875 (Open Web Text)

Max Activating Token Index: 24

Text #11

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4267. Min Act: -0.1637

Data Index: 4132524 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4186. Min Act: -0.1554

Data Index: 5659939 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4177. Min Act: -0.1531

Data Index: 1554199 (Open Web Text)

Max Activating Token Index: 27

Text #14

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4202. Min Act: -0.1605

Data Index: 6957118 (Open Web Text)

Max Activating Token Index: 29

Text #15

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4159. Min Act: -0.1628

Data Index: 4263331 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4182. Min Act: -0.1510

Data Index: 2584667 (Open Web Text)

Max Activating Token Index: 28

Text #17

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4181. Min Act: -0.1564

Data Index: 4609224 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4255. Min Act: -0.1632

Data Index: 7824015 (Open Web Text)

Max Activating Token Index: 25

Text #19

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4195. Min Act: -0.1633

Data Index: 2089329 (Open Web Text)

Max Activating Token Index: 20