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

Dataset: Open Web Text

Neuron 1655 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: 5.0296. Min Range: -5.0296

Max Act: 5.0296. Min Act: -0.1700

Data Index: 4100203 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.9912. Min Act: -0.1700

Data Index: 5418715 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.9485. Min Act: -0.1700

Data Index: 4499543 (Open Web Text)

Max Activating Token Index: 127

Text #3

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.9442. Min Act: -0.1700

Data Index: 1426148 (Open Web Text)

Max Activating Token Index: 139

Text #4

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.9556. Min Act: -0.1700

Data Index: 1159982 (Open Web Text)

Max Activating Token Index: 441

Text #5

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.9301. Min Act: -0.1700

Data Index: 1231244 (Open Web Text)

Max Activating Token Index: 1002

Text #6

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.9158. Min Act: -0.1700

Data Index: 4117747 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.9206. Min Act: -0.1700

Data Index: 2238083 (Open Web Text)

Max Activating Token Index: 460

Text #8

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.9505. Min Act: -0.1700

Data Index: 1491051 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.8917. Min Act: -0.1700

Data Index: 5885400 (Open Web Text)

Max Activating Token Index: 997

Text #10

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.9063. Min Act: -0.1700

Data Index: 224668 (Open Web Text)

Max Activating Token Index: 579

Text #11

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.8968. Min Act: -0.1700

Data Index: 1667706 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.9002. Min Act: -0.1700

Data Index: 8513312 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.9130. Min Act: -0.1700

Data Index: 3135579 (Open Web Text)

Max Activating Token Index: 523

Text #14

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.8922. Min Act: -0.1700

Data Index: 337638 (Open Web Text)

Max Activating Token Index: 104

Text #15

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.8788. Min Act: -0.1700

Data Index: 1836500 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.9002. Min Act: -0.1700

Data Index: 3206513 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.8514. Min Act: -0.1700

Data Index: 1624843 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.8646. Min Act: -0.1700

Data Index: 940265 (Open Web Text)

Max Activating Token Index: 33

Text #19

Max Range: 5.0296. Min Range: -5.0296

Max Act: 4.8438. Min Act: -0.1700

Data Index: 4210585 (Open Web Text)

Max Activating Token Index: 845