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

Dataset: Open Web Text

Neuron 613 in Layer 1

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: 0.4582. Min Range: -0.4582

Max Act: 0.4582. Min Act: -0.1700

Data Index: 4865706 (Open Web Text)

Max Activating Token Index: 240

Text #1

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3994. Min Act: -0.1696

Data Index: 1901807 (Open Web Text)

Max Activating Token Index: 418

Text #2

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4062. Min Act: -0.1699

Data Index: 4153526 (Open Web Text)

Max Activating Token Index: 185

Text #3

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3876. Min Act: -0.1695

Data Index: 343341 (Open Web Text)

Max Activating Token Index: 489

Text #4

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3835. Min Act: -0.1700

Data Index: 3680140 (Open Web Text)

Max Activating Token Index: 387

Text #5

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3876. Min Act: -0.1700

Data Index: 6327775 (Open Web Text)

Max Activating Token Index: 1006

Text #6

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3892. Min Act: -0.1697

Data Index: 2785497 (Open Web Text)

Max Activating Token Index: 698

Text #7

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3889. Min Act: -0.1700

Data Index: 2889157 (Open Web Text)

Max Activating Token Index: 1009

Text #8

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3843. Min Act: -0.1696

Data Index: 1789220 (Open Web Text)

Max Activating Token Index: 558

Text #9

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3771. Min Act: -0.1700

Data Index: 5531383 (Open Web Text)

Max Activating Token Index: 94

Text #10

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3866. Min Act: -0.1699

Data Index: 6486350 (Open Web Text)

Max Activating Token Index: 512

Text #11

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3847. Min Act: -0.1700

Data Index: 272291 (Open Web Text)

Max Activating Token Index: 650

Text #12

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3780. Min Act: -0.1700

Data Index: 1939923 (Open Web Text)

Max Activating Token Index: 732

Text #13

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3630. Min Act: -0.1700

Data Index: 4940291 (Open Web Text)

Max Activating Token Index: 798

Text #14

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3756. Min Act: -0.1700

Data Index: 4675483 (Open Web Text)

Max Activating Token Index: 609

Text #15

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3655. Min Act: -0.1700

Data Index: 207921 (Open Web Text)

Max Activating Token Index: 367

Text #16

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3640. Min Act: -0.1700

Data Index: 4756081 (Open Web Text)

Max Activating Token Index: 370

Text #17

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3612. Min Act: -0.1697

Data Index: 5957380 (Open Web Text)

Max Activating Token Index: 592

Text #18

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3629. Min Act: -0.1700

Data Index: 3944410 (Open Web Text)

Max Activating Token Index: 589

Text #19

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3548. Min Act: -0.1700

Data Index: 2418630 (Open Web Text)

Max Activating Token Index: 210