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

Dataset: Open Web Text

Neuron 1610 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: 5.5675. Min Range: -5.5675

Max Act: 5.5675. Min Act: -0.1699

Data Index: 5628588 (Open Web Text)

Max Activating Token Index: 250

Text #1

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.8304. Min Act: -0.1700

Data Index: 4002019 (Open Web Text)

Max Activating Token Index: 897

Text #2

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.8352. Min Act: -0.1700

Data Index: 7238387 (Open Web Text)

Max Activating Token Index: 207

Text #3

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.8239. Min Act: -0.1700

Data Index: 6523040 (Open Web Text)

Max Activating Token Index: 397

Text #4

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.7684. Min Act: -0.1700

Data Index: 3545960 (Open Web Text)

Max Activating Token Index: 568

Text #5

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.7624. Min Act: -0.1700

Data Index: 4483431 (Open Web Text)

Max Activating Token Index: 939

Text #6

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.7244. Min Act: -0.1700

Data Index: 7537088 (Open Web Text)

Max Activating Token Index: 566

Text #7

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.7313. Min Act: -0.1700

Data Index: 16531 (Open Web Text)

Max Activating Token Index: 74

Text #8

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.6985. Min Act: -0.1700

Data Index: 2006027 (Open Web Text)

Max Activating Token Index: 376

Text #9

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.6540. Min Act: -0.1700

Data Index: 4177298 (Open Web Text)

Max Activating Token Index: 128

Text #10

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.6607. Min Act: -0.1700

Data Index: 8665898 (Open Web Text)

Max Activating Token Index: 728

Text #11

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.6389. Min Act: -0.1700

Data Index: 3065000 (Open Web Text)

Max Activating Token Index: 1021

Text #12

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.6467. Min Act: -0.1700

Data Index: 6370163 (Open Web Text)

Max Activating Token Index: 480

Text #13

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.6420. Min Act: -0.1700

Data Index: 6216664 (Open Web Text)

Max Activating Token Index: 956

Text #14

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.6393. Min Act: -0.1700

Data Index: 3568089 (Open Web Text)

Max Activating Token Index: 918

Text #15

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.6184. Min Act: -0.1700

Data Index: 4254994 (Open Web Text)

Max Activating Token Index: 541

Text #16

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.6055. Min Act: -0.1700

Data Index: 4807181 (Open Web Text)

Max Activating Token Index: 314

Text #17

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.6680. Min Act: -0.1700

Data Index: 6786494 (Open Web Text)

Max Activating Token Index: 898

Text #18

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.6387. Min Act: -0.1700

Data Index: 4268624 (Open Web Text)

Max Activating Token Index: 895

Text #19

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.6260. Min Act: -0.1700

Data Index: 5154494 (Open Web Text)

Max Activating Token Index: 851