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

Dataset: Open Web Text

Neuron 178 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: 4.5682. Min Range: -4.5682

Max Act: 4.5682. Min Act: -0.1700

Data Index: 6860484 (Open Web Text)

Max Activating Token Index: 775

Text #1

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.4783. Min Act: -0.1700

Data Index: 5764716 (Open Web Text)

Max Activating Token Index: 147

Text #2

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.4858. Min Act: -0.1700

Data Index: 7001461 (Open Web Text)

Max Activating Token Index: 944

Text #3

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.4193. Min Act: -0.1700

Data Index: 1404537 (Open Web Text)

Max Activating Token Index: 639

Text #4

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.3881. Min Act: -0.1700

Data Index: 5984990 (Open Web Text)

Max Activating Token Index: 838

Text #5

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.3986. Min Act: -0.1700

Data Index: 6129000 (Open Web Text)

Max Activating Token Index: 524

Text #6

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.3913. Min Act: -0.1700

Data Index: 2718558 (Open Web Text)

Max Activating Token Index: 111

Text #7

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.3459. Min Act: -0.1700

Data Index: 1890 (Open Web Text)

Max Activating Token Index: 66

Text #8

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.3777. Min Act: -0.1700

Data Index: 3726126 (Open Web Text)

Max Activating Token Index: 247

Text #9

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.3681. Min Act: -0.1700

Data Index: 6277884 (Open Web Text)

Max Activating Token Index: 590

Text #10

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.3270. Min Act: -0.1700

Data Index: 2383352 (Open Web Text)

Max Activating Token Index: 386

Text #11

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.3395. Min Act: -0.1700

Data Index: 3863711 (Open Web Text)

Max Activating Token Index: 338

Text #12

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.3237. Min Act: -0.1700

Data Index: 8229667 (Open Web Text)

Max Activating Token Index: 915

Text #13

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.3526. Min Act: -0.1700

Data Index: 3915392 (Open Web Text)

Max Activating Token Index: 941

Text #14

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.3534. Min Act: -0.1700

Data Index: 4074410 (Open Web Text)

Max Activating Token Index: 755

Text #15

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.3214. Min Act: -0.1700

Data Index: 3909778 (Open Web Text)

Max Activating Token Index: 938

Text #16

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.2984. Min Act: -0.1700

Data Index: 1191585 (Open Web Text)

Max Activating Token Index: 406

Text #17

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.3049. Min Act: -0.1700

Data Index: 1881364 (Open Web Text)

Max Activating Token Index: 542

Text #18

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.3158. Min Act: -0.1700

Data Index: 3155952 (Open Web Text)

Max Activating Token Index: 469

Text #19

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.2889. Min Act: -0.1700

Data Index: 4837163 (Open Web Text)

Max Activating Token Index: 864