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

Dataset: Open Web Text

Neuron 2382 in Layer 5

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: 4.1707. Min Range: -4.1707

Max Act: 4.1707. Min Act: -0.1700

Data Index: 6899067 (Open Web Text)

Max Activating Token Index: 513

Text #1

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0951. Min Act: -0.1700

Data Index: 7684882 (Open Web Text)

Max Activating Token Index: 567

Text #2

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0807. Min Act: -0.1700

Data Index: 7190232 (Open Web Text)

Max Activating Token Index: 502

Text #3

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0824. Min Act: -0.1700

Data Index: 2357282 (Open Web Text)

Max Activating Token Index: 434

Text #4

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0789. Min Act: -0.1700

Data Index: 3752670 (Open Web Text)

Max Activating Token Index: 738

Text #5

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0324. Min Act: -0.1700

Data Index: 6363698 (Open Web Text)

Max Activating Token Index: 634

Text #6

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0491. Min Act: -0.1700

Data Index: 1823237 (Open Web Text)

Max Activating Token Index: 548

Text #7

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0533. Min Act: -0.1700

Data Index: 6616149 (Open Web Text)

Max Activating Token Index: 41

Text #8

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0681. Min Act: -0.1700

Data Index: 999671 (Open Web Text)

Max Activating Token Index: 450

Text #9

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0527. Min Act: -0.1700

Data Index: 8311791 (Open Web Text)

Max Activating Token Index: 501

Text #10

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0529. Min Act: -0.1700

Data Index: 7204600 (Open Web Text)

Max Activating Token Index: 569

Text #11

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0271. Min Act: -0.1700

Data Index: 3649553 (Open Web Text)

Max Activating Token Index: 49

Text #12

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0290. Min Act: -0.1700

Data Index: 2947692 (Open Web Text)

Max Activating Token Index: 590

Text #13

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0113. Min Act: -0.1700

Data Index: 4287093 (Open Web Text)

Max Activating Token Index: 591

Text #14

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0308. Min Act: -0.1700

Data Index: 4403109 (Open Web Text)

Max Activating Token Index: 613

Text #15

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0087. Min Act: -0.1700

Data Index: 4707284 (Open Web Text)

Max Activating Token Index: 897

Text #16

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0372. Min Act: -0.1700

Data Index: 643267 (Open Web Text)

Max Activating Token Index: 578

Text #17

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0159. Min Act: -0.1700

Data Index: 6813303 (Open Web Text)

Max Activating Token Index: 369

Text #18

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0350. Min Act: -0.1700

Data Index: 693807 (Open Web Text)

Max Activating Token Index: 574

Text #19

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0265. Min Act: -0.1700

Data Index: 7147554 (Open Web Text)

Max Activating Token Index: 467