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

Dataset: Open Web Text

Neuron 1251 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: 3.0346. Min Range: -3.0346

Max Act: 3.0346. Min Act: -0.1700

Data Index: 1940438 (Open Web Text)

Max Activating Token Index: 108

Text #1

Max Range: 3.0346. Min Range: -3.0346

Max Act: 3.0142. Min Act: -0.1700

Data Index: 6164368 (Open Web Text)

Max Activating Token Index: 797

Text #2

Max Range: 3.0346. Min Range: -3.0346

Max Act: 3.0270. Min Act: -0.1700

Data Index: 477989 (Open Web Text)

Max Activating Token Index: 698

Text #3

Max Range: 3.0346. Min Range: -3.0346

Max Act: 3.0106. Min Act: -0.1700

Data Index: 6682506 (Open Web Text)

Max Activating Token Index: 522

Text #4

Max Range: 3.0346. Min Range: -3.0346

Max Act: 3.0094. Min Act: -0.1700

Data Index: 7797338 (Open Web Text)

Max Activating Token Index: 622

Text #5

Max Range: 3.0346. Min Range: -3.0346

Max Act: 2.9877. Min Act: -0.1700

Data Index: 3983151 (Open Web Text)

Max Activating Token Index: 520

Text #6

Max Range: 3.0346. Min Range: -3.0346

Max Act: 2.9962. Min Act: -0.1700

Data Index: 4115531 (Open Web Text)

Max Activating Token Index: 731

Text #7

Max Range: 3.0346. Min Range: -3.0346

Max Act: 3.0197. Min Act: -0.1700

Data Index: 5305455 (Open Web Text)

Max Activating Token Index: 632

Text #8

Max Range: 3.0346. Min Range: -3.0346

Max Act: 2.9937. Min Act: -0.1700

Data Index: 1317028 (Open Web Text)

Max Activating Token Index: 848

Text #9

Max Range: 3.0346. Min Range: -3.0346

Max Act: 3.0140. Min Act: -0.1700

Data Index: 6177445 (Open Web Text)

Max Activating Token Index: 603

Text #10

Max Range: 3.0346. Min Range: -3.0346

Max Act: 2.9656. Min Act: -0.1700

Data Index: 3474106 (Open Web Text)

Max Activating Token Index: 653

Text #11

Max Range: 3.0346. Min Range: -3.0346

Max Act: 2.9927. Min Act: -0.1700

Data Index: 8046786 (Open Web Text)

Max Activating Token Index: 650

Text #12

Max Range: 3.0346. Min Range: -3.0346

Max Act: 2.9658. Min Act: -0.1700

Data Index: 3111163 (Open Web Text)

Max Activating Token Index: 137

Text #13

Max Range: 3.0346. Min Range: -3.0346

Max Act: 2.9772. Min Act: -0.1700

Data Index: 7005502 (Open Web Text)

Max Activating Token Index: 83

Text #14

Max Range: 3.0346. Min Range: -3.0346

Max Act: 2.9587. Min Act: -0.1700

Data Index: 917918 (Open Web Text)

Max Activating Token Index: 664

Text #15

Max Range: 3.0346. Min Range: -3.0346

Max Act: 2.9385. Min Act: -0.1700

Data Index: 7391286 (Open Web Text)

Max Activating Token Index: 364

Text #16

Max Range: 3.0346. Min Range: -3.0346

Max Act: 2.9656. Min Act: -0.1700

Data Index: 5678707 (Open Web Text)

Max Activating Token Index: 429

Text #17

Max Range: 3.0346. Min Range: -3.0346

Max Act: 2.9742. Min Act: -0.1700

Data Index: 7150025 (Open Web Text)

Max Activating Token Index: 342

Text #18

Max Range: 3.0346. Min Range: -3.0346

Max Act: 2.9308. Min Act: -0.1700

Data Index: 3392953 (Open Web Text)

Max Activating Token Index: 235

Text #19

Max Range: 3.0346. Min Range: -3.0346

Max Act: 2.9571. Min Act: -0.1700

Data Index: 7261226 (Open Web Text)

Max Activating Token Index: 990