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

Dataset: Open Web Text

Neuron 500 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: 4.0695. Min Range: -4.0695

Max Act: 4.0695. Min Act: -0.1700

Data Index: 7608389 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.9299. Min Act: -0.1700

Data Index: 8001900 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8918. Min Act: -0.1700

Data Index: 5573155 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8978. Min Act: -0.1700

Data Index: 8280997 (Open Web Text)

Max Activating Token Index: 17

Text #4

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8614. Min Act: -0.1700

Data Index: 7053208 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8630. Min Act: -0.1700

Data Index: 2913147 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8657. Min Act: -0.1700

Data Index: 4878112 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8497. Min Act: -0.1700

Data Index: 3687670 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8536. Min Act: -0.1700

Data Index: 8675613 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8336. Min Act: -0.1700

Data Index: 4874618 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8195. Min Act: -0.1700

Data Index: 5139538 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8397. Min Act: -0.1700

Data Index: 7360 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8484. Min Act: -0.1700

Data Index: 1583101 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8463. Min Act: -0.1700

Data Index: 7013513 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8432. Min Act: -0.1700

Data Index: 8111470 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8413. Min Act: -0.1700

Data Index: 3106675 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8026. Min Act: -0.1700

Data Index: 4289070 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.7839. Min Act: -0.1700

Data Index: 1558626 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.7952. Min Act: -0.1700

Data Index: 6833721 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8032. Min Act: -0.1700

Data Index: 2371063 (Open Web Text)

Max Activating Token Index: 355