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

Dataset: Open Web Text

Neuron 271 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: 4.9764. Min Range: -4.9764

Max Act: 4.9764. Min Act: -0.1700

Data Index: 221523 (Open Web Text)

Max Activating Token Index: 587

Text #1

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.9753. Min Act: -0.1700

Data Index: 8213933 (Open Web Text)

Max Activating Token Index: 493

Text #2

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.9086. Min Act: -0.1700

Data Index: 8213932 (Open Web Text)

Max Activating Token Index: 1000

Text #3

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.8864. Min Act: -0.1700

Data Index: 7204882 (Open Web Text)

Max Activating Token Index: 272

Text #4

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.8879. Min Act: -0.1700

Data Index: 7822975 (Open Web Text)

Max Activating Token Index: 338

Text #5

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.8220. Min Act: -0.1700

Data Index: 6578510 (Open Web Text)

Max Activating Token Index: 893

Text #6

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.8822. Min Act: -0.1700

Data Index: 5287602 (Open Web Text)

Max Activating Token Index: 437

Text #7

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.8271. Min Act: -0.1700

Data Index: 5033566 (Open Web Text)

Max Activating Token Index: 545

Text #8

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.8010. Min Act: -0.1700

Data Index: 1635631 (Open Web Text)

Max Activating Token Index: 438

Text #9

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.8384. Min Act: -0.1700

Data Index: 5667951 (Open Web Text)

Max Activating Token Index: 333

Text #10

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.8017. Min Act: -0.1700

Data Index: 552710 (Open Web Text)

Max Activating Token Index: 533

Text #11

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.7364. Min Act: -0.1700

Data Index: 7345525 (Open Web Text)

Max Activating Token Index: 256

Text #12

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.7543. Min Act: -0.1700

Data Index: 7684704 (Open Web Text)

Max Activating Token Index: 473

Text #13

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.7572. Min Act: -0.1700

Data Index: 1746380 (Open Web Text)

Max Activating Token Index: 268

Text #14

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.7434. Min Act: -0.1700

Data Index: 8186769 (Open Web Text)

Max Activating Token Index: 145

Text #15

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.7760. Min Act: -0.1700

Data Index: 892610 (Open Web Text)

Max Activating Token Index: 356

Text #16

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.7588. Min Act: -0.1700

Data Index: 7911885 (Open Web Text)

Max Activating Token Index: 388

Text #17

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.7616. Min Act: -0.1700

Data Index: 3652097 (Open Web Text)

Max Activating Token Index: 125

Text #18

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.7522. Min Act: -0.1700

Data Index: 7014322 (Open Web Text)

Max Activating Token Index: 149

Text #19

Max Range: 4.9764. Min Range: -4.9764

Max Act: 4.7172. Min Act: -0.1700

Data Index: 3510950 (Open Web Text)

Max Activating Token Index: 390