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

Dataset: Open Web Text

Neuron 743 in Layer 4

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: 3.6541. Min Range: -3.6541

Max Act: 3.6541. Min Act: -0.1700

Data Index: 962560 (Open Web Text)

Max Activating Token Index: 455

Text #1

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.6397. Min Act: -0.1700

Data Index: 529730 (Open Web Text)

Max Activating Token Index: 905

Text #2

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.6152. Min Act: -0.1700

Data Index: 1065033 (Open Web Text)

Max Activating Token Index: 67

Text #3

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.6208. Min Act: -0.1700

Data Index: 2479582 (Open Web Text)

Max Activating Token Index: 386

Text #4

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.5980. Min Act: -0.1700

Data Index: 4552739 (Open Web Text)

Max Activating Token Index: 322

Text #5

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.6039. Min Act: -0.1700

Data Index: 611781 (Open Web Text)

Max Activating Token Index: 113

Text #6

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.6185. Min Act: -0.1700

Data Index: 2093228 (Open Web Text)

Max Activating Token Index: 461

Text #7

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.6210. Min Act: -0.1700

Data Index: 498825 (Open Web Text)

Max Activating Token Index: 519

Text #8

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.6060. Min Act: -0.1700

Data Index: 6567031 (Open Web Text)

Max Activating Token Index: 913

Text #9

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.5860. Min Act: -0.1700

Data Index: 4788585 (Open Web Text)

Max Activating Token Index: 422

Text #10

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.5725. Min Act: -0.1700

Data Index: 19648 (Open Web Text)

Max Activating Token Index: 898

Text #11

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.6021. Min Act: -0.1700

Data Index: 1927192 (Open Web Text)

Max Activating Token Index: 984

Text #12

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.5900. Min Act: -0.1700

Data Index: 1356225 (Open Web Text)

Max Activating Token Index: 367

Text #13

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.5668. Min Act: -0.1700

Data Index: 2006352 (Open Web Text)

Max Activating Token Index: 297

Text #14

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.5735. Min Act: -0.1700

Data Index: 122861 (Open Web Text)

Max Activating Token Index: 748

Text #15

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.5744. Min Act: -0.1700

Data Index: 6504875 (Open Web Text)

Max Activating Token Index: 308

Text #16

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.5613. Min Act: -0.1700

Data Index: 1010854 (Open Web Text)

Max Activating Token Index: 877

Text #17

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.5399. Min Act: -0.1700

Data Index: 4289247 (Open Web Text)

Max Activating Token Index: 712

Text #18

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.5630. Min Act: -0.1700

Data Index: 4240233 (Open Web Text)

Max Activating Token Index: 87

Text #19

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.5623. Min Act: -0.1700

Data Index: 7464525 (Open Web Text)

Max Activating Token Index: 33