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

Dataset: Open Web Text

Neuron 1219 in Layer 5

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: 5.1962. Min Range: -5.1962

Max Act: 5.1702. Min Act: -0.1700

Data Index: 4496890 (Open Web Text)

Max Activating Token Index: 377

Text #1

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.1962. Min Act: -0.1700

Data Index: 6611194 (Open Web Text)

Max Activating Token Index: 804

Text #2

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.1689. Min Act: -0.1700

Data Index: 1413564 (Open Web Text)

Max Activating Token Index: 964

Text #3

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.1898. Min Act: -0.1700

Data Index: 6399033 (Open Web Text)

Max Activating Token Index: 885

Text #4

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.1388. Min Act: -0.1700

Data Index: 3599249 (Open Web Text)

Max Activating Token Index: 687

Text #5

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.1222. Min Act: -0.1700

Data Index: 2562154 (Open Web Text)

Max Activating Token Index: 365

Text #6

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.1295. Min Act: -0.1700

Data Index: 8477107 (Open Web Text)

Max Activating Token Index: 639

Text #7

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.1539. Min Act: -0.1700

Data Index: 5970930 (Open Web Text)

Max Activating Token Index: 1008

Text #8

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.0803. Min Act: -0.1700

Data Index: 7397210 (Open Web Text)

Max Activating Token Index: 578

Text #9

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.1008. Min Act: -0.1700

Data Index: 7267221 (Open Web Text)

Max Activating Token Index: 812

Text #10

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.1052. Min Act: -0.1700

Data Index: 7131622 (Open Web Text)

Max Activating Token Index: 333

Text #11

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.1083. Min Act: -0.1700

Data Index: 3536432 (Open Web Text)

Max Activating Token Index: 500

Text #12

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.0974. Min Act: -0.1700

Data Index: 6934060 (Open Web Text)

Max Activating Token Index: 1005

Text #13

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.1150. Min Act: -0.1700

Data Index: 280287 (Open Web Text)

Max Activating Token Index: 547

Text #14

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.1007. Min Act: -0.1700

Data Index: 6695070 (Open Web Text)

Max Activating Token Index: 271

Text #15

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.1373. Min Act: -0.1700

Data Index: 6607604 (Open Web Text)

Max Activating Token Index: 395

Text #16

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.1131. Min Act: -0.1700

Data Index: 6607598 (Open Web Text)

Max Activating Token Index: 741

Text #17

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.0792. Min Act: -0.1700

Data Index: 5722580 (Open Web Text)

Max Activating Token Index: 402

Text #18

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.1261. Min Act: -0.1700

Data Index: 4890731 (Open Web Text)

Max Activating Token Index: 863

Text #19

Max Range: 5.1962. Min Range: -5.1962

Max Act: 5.0973. Min Act: -0.1700

Data Index: 4603749 (Open Web Text)

Max Activating Token Index: 604