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

Dataset: Open Web Text

Neuron 2849 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: 3.5672. Min Range: -3.5672

Max Act: 3.5672. Min Act: -0.1700

Data Index: 4963197 (Open Web Text)

Max Activating Token Index: 461

Text #1

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.5422. Min Act: -0.1700

Data Index: 6423509 (Open Web Text)

Max Activating Token Index: 490

Text #2

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.5429. Min Act: -0.1700

Data Index: 7809749 (Open Web Text)

Max Activating Token Index: 458

Text #3

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.4767. Min Act: -0.1700

Data Index: 6478596 (Open Web Text)

Max Activating Token Index: 628

Text #4

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.4470. Min Act: -0.1700

Data Index: 6361091 (Open Web Text)

Max Activating Token Index: 968

Text #5

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.4302. Min Act: -0.1700

Data Index: 3740977 (Open Web Text)

Max Activating Token Index: 567

Text #6

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.4210. Min Act: -0.1700

Data Index: 2952131 (Open Web Text)

Max Activating Token Index: 517

Text #7

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3900. Min Act: -0.1700

Data Index: 834112 (Open Web Text)

Max Activating Token Index: 290

Text #8

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3712. Min Act: -0.1700

Data Index: 4898674 (Open Web Text)

Max Activating Token Index: 600

Text #9

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3982. Min Act: -0.1700

Data Index: 5181868 (Open Web Text)

Max Activating Token Index: 404

Text #10

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3764. Min Act: -0.1700

Data Index: 7683243 (Open Web Text)

Max Activating Token Index: 413

Text #11

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3518. Min Act: -0.1700

Data Index: 6728145 (Open Web Text)

Max Activating Token Index: 406

Text #12

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3562. Min Act: -0.1700

Data Index: 86416 (Open Web Text)

Max Activating Token Index: 277

Text #13

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3605. Min Act: -0.1700

Data Index: 6769153 (Open Web Text)

Max Activating Token Index: 497

Text #14

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3023. Min Act: -0.1700

Data Index: 2957591 (Open Web Text)

Max Activating Token Index: 1007

Text #15

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3275. Min Act: -0.1700

Data Index: 8566352 (Open Web Text)

Max Activating Token Index: 286

Text #16

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3090. Min Act: -0.1700

Data Index: 6437997 (Open Web Text)

Max Activating Token Index: 344

Text #17

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3232. Min Act: -0.1700

Data Index: 5909843 (Open Web Text)

Max Activating Token Index: 918

Text #18

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3364. Min Act: -0.1700

Data Index: 708923 (Open Web Text)

Max Activating Token Index: 569

Text #19

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.2917. Min Act: -0.1700

Data Index: 7120401 (Open Web Text)

Max Activating Token Index: 285