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

Dataset: Open Web Text

Neuron 1219 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: 3.2333. Min Range: -3.2333

Max Act: 3.2333. Min Act: -0.1700

Data Index: 5920807 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.2303. Min Act: -0.1700

Data Index: 3718595 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1783. Min Act: -0.1700

Data Index: 4832541 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1665. Min Act: -0.1700

Data Index: 88631 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1590. Min Act: -0.1700

Data Index: 4522587 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1586. Min Act: -0.1700

Data Index: 4730971 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1606. Min Act: -0.1700

Data Index: 2290698 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1380. Min Act: -0.1700

Data Index: 6329738 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1332. Min Act: -0.1700

Data Index: 7441530 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1402. Min Act: -0.1700

Data Index: 5144447 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1400. Min Act: -0.1700

Data Index: 4759487 (Open Web Text)

Max Activating Token Index: 1019

Text #11

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1316. Min Act: -0.1700

Data Index: 3880914 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1168. Min Act: -0.1700

Data Index: 735421 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1283. Min Act: -0.1700

Data Index: 2360221 (Open Web Text)

Max Activating Token Index: 48

Text #14

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1327. Min Act: -0.1700

Data Index: 4833216 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1088. Min Act: -0.1700

Data Index: 8261011 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1203. Min Act: -0.1700

Data Index: 4819833 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1071. Min Act: -0.1700

Data Index: 7285207 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1076. Min Act: -0.1700

Data Index: 4182688 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.0853. Min Act: -0.1700

Data Index: 5717822 (Open Web Text)

Max Activating Token Index: 4