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

Dataset: Open Web Text

Neuron 822 in Layer 2

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: 1.9421. Min Range: -1.9421

Max Act: 1.9421. Min Act: -0.1700

Data Index: 4752170 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.9029. Min Act: -0.1700

Data Index: 7931992 (Open Web Text)

Max Activating Token Index: 863

Text #2

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8714. Min Act: -0.1700

Data Index: 1464024 (Open Web Text)

Max Activating Token Index: 530

Text #3

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8596. Min Act: -0.1700

Data Index: 7122489 (Open Web Text)

Max Activating Token Index: 54

Text #4

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8627. Min Act: -0.1700

Data Index: 7510784 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8649. Min Act: -0.1700

Data Index: 5191777 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8661. Min Act: -0.1698

Data Index: 5796299 (Open Web Text)

Max Activating Token Index: 61

Text #7

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8604. Min Act: -0.1700

Data Index: 7269393 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8467. Min Act: -0.1700

Data Index: 5014421 (Open Web Text)

Max Activating Token Index: 145

Text #9

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8409. Min Act: -0.1700

Data Index: 2339976 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8324. Min Act: -0.1700

Data Index: 5802424 (Open Web Text)

Max Activating Token Index: 393

Text #11

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8347. Min Act: -0.1700

Data Index: 5137642 (Open Web Text)

Max Activating Token Index: 720

Text #12

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8406. Min Act: -0.1700

Data Index: 3874640 (Open Web Text)

Max Activating Token Index: 930

Text #13

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8326. Min Act: -0.1700

Data Index: 1288306 (Open Web Text)

Max Activating Token Index: 103

Text #14

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8321. Min Act: -0.1700

Data Index: 3025103 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8315. Min Act: -0.1700

Data Index: 3272354 (Open Web Text)

Max Activating Token Index: 1003

Text #16

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8080. Min Act: -0.1700

Data Index: 1650361 (Open Web Text)

Max Activating Token Index: 214

Text #17

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8135. Min Act: -0.1700

Data Index: 2074095 (Open Web Text)

Max Activating Token Index: 29

Text #18

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8155. Min Act: -0.1700

Data Index: 7664153 (Open Web Text)

Max Activating Token Index: 593

Text #19

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.8126. Min Act: -0.1700

Data Index: 237291 (Open Web Text)

Max Activating Token Index: 289