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

Dataset: Open Web Text

Neuron 2202 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: 3.1184. Min Range: -3.1184

Max Act: 3.1184. Min Act: -0.1700

Data Index: 8708589 (Open Web Text)

Max Activating Token Index: 384

Text #1

Max Range: 3.1184. Min Range: -3.1184

Max Act: 3.0199. Min Act: -0.1700

Data Index: 3927847 (Open Web Text)

Max Activating Token Index: 553

Text #2

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.8514. Min Act: -0.1700

Data Index: 764580 (Open Web Text)

Max Activating Token Index: 855

Text #3

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.8366. Min Act: -0.1700

Data Index: 7878778 (Open Web Text)

Max Activating Token Index: 315

Text #4

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.8320. Min Act: -0.1700

Data Index: 5560667 (Open Web Text)

Max Activating Token Index: 420

Text #5

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.8318. Min Act: -0.1700

Data Index: 3047151 (Open Web Text)

Max Activating Token Index: 487

Text #6

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.8024. Min Act: -0.1700

Data Index: 6670943 (Open Web Text)

Max Activating Token Index: 382

Text #7

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.8020. Min Act: -0.1700

Data Index: 2399959 (Open Web Text)

Max Activating Token Index: 965

Text #8

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.7504. Min Act: -0.1700

Data Index: 8328675 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.7709. Min Act: -0.1700

Data Index: 1476576 (Open Web Text)

Max Activating Token Index: 722

Text #10

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.7348. Min Act: -0.1700

Data Index: 7040063 (Open Web Text)

Max Activating Token Index: 157

Text #11

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.7218. Min Act: -0.1700

Data Index: 359195 (Open Web Text)

Max Activating Token Index: 369

Text #12

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.7200. Min Act: -0.1700

Data Index: 7273747 (Open Web Text)

Max Activating Token Index: 586

Text #13

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.7174. Min Act: -0.1700

Data Index: 8292553 (Open Web Text)

Max Activating Token Index: 864

Text #14

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.7337. Min Act: -0.1700

Data Index: 4778170 (Open Web Text)

Max Activating Token Index: 652

Text #15

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.7010. Min Act: -0.1700

Data Index: 2860779 (Open Web Text)

Max Activating Token Index: 591

Text #16

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.7220. Min Act: -0.1700

Data Index: 5155410 (Open Web Text)

Max Activating Token Index: 600

Text #17

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.6924. Min Act: -0.1700

Data Index: 165163 (Open Web Text)

Max Activating Token Index: 896

Text #18

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.6990. Min Act: -0.1700

Data Index: 8057795 (Open Web Text)

Max Activating Token Index: 826

Text #19

Max Range: 3.1184. Min Range: -3.1184

Max Act: 2.6855. Min Act: -0.1700

Data Index: 1977599 (Open Web Text)

Max Activating Token Index: 904