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

Dataset: Open Web Text

Neuron 1258 in Layer 6

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: 3.7433. Min Range: -3.7433

Max Act: 3.7433. Min Act: -0.1700

Data Index: 6313160 (Open Web Text)

Max Activating Token Index: 477

Text #1

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.7176. Min Act: -0.1700

Data Index: 8099176 (Open Web Text)

Max Activating Token Index: 530

Text #2

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.6556. Min Act: -0.1700

Data Index: 8550520 (Open Web Text)

Max Activating Token Index: 187

Text #3

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.6813. Min Act: -0.1700

Data Index: 2259184 (Open Web Text)

Max Activating Token Index: 541

Text #4

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.6326. Min Act: -0.1700

Data Index: 2156056 (Open Web Text)

Max Activating Token Index: 640

Text #5

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.6060. Min Act: -0.1700

Data Index: 1236377 (Open Web Text)

Max Activating Token Index: 999

Text #6

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.6038. Min Act: -0.1700

Data Index: 6322088 (Open Web Text)

Max Activating Token Index: 463

Text #7

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.5839. Min Act: -0.1700

Data Index: 7488259 (Open Web Text)

Max Activating Token Index: 894

Text #8

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.5556. Min Act: -0.1700

Data Index: 6048821 (Open Web Text)

Max Activating Token Index: 1012

Text #9

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.5666. Min Act: -0.1700

Data Index: 2121854 (Open Web Text)

Max Activating Token Index: 579

Text #10

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.5638. Min Act: -0.1700

Data Index: 4885234 (Open Web Text)

Max Activating Token Index: 198

Text #11

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.5283. Min Act: -0.1700

Data Index: 8805491 (Open Web Text)

Max Activating Token Index: 584

Text #12

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.5355. Min Act: -0.1700

Data Index: 6372939 (Open Web Text)

Max Activating Token Index: 284

Text #13

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.5633. Min Act: -0.1700

Data Index: 7467206 (Open Web Text)

Max Activating Token Index: 124

Text #14

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.5506. Min Act: -0.1700

Data Index: 6840402 (Open Web Text)

Max Activating Token Index: 68

Text #15

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.5316. Min Act: -0.1700

Data Index: 5413576 (Open Web Text)

Max Activating Token Index: 580

Text #16

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.5327. Min Act: -0.1700

Data Index: 4727896 (Open Web Text)

Max Activating Token Index: 955

Text #17

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.5120. Min Act: -0.1700

Data Index: 7368089 (Open Web Text)

Max Activating Token Index: 389

Text #18

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.5185. Min Act: -0.1700

Data Index: 7982721 (Open Web Text)

Max Activating Token Index: 440

Text #19

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.5302. Min Act: -0.1700

Data Index: 3049535 (Open Web Text)

Max Activating Token Index: 486