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

Dataset: Open Web Text

Neuron 916 in Layer 2

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: 3.9498. Min Range: -3.9498

Max Act: 3.9498. Min Act: -0.1700

Data Index: 5723670 (Open Web Text)

Max Activating Token Index: 372

Text #1

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.9238. Min Act: -0.1700

Data Index: 5968924 (Open Web Text)

Max Activating Token Index: 58

Text #2

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.8997. Min Act: -0.1700

Data Index: 8354106 (Open Web Text)

Max Activating Token Index: 134

Text #3

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.8519. Min Act: -0.1700

Data Index: 5926223 (Open Web Text)

Max Activating Token Index: 605

Text #4

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.8592. Min Act: -0.1700

Data Index: 12166 (Open Web Text)

Max Activating Token Index: 69

Text #5

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.8317. Min Act: -0.1700

Data Index: 2826949 (Open Web Text)

Max Activating Token Index: 458

Text #6

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.8424. Min Act: -0.1700

Data Index: 5976944 (Open Web Text)

Max Activating Token Index: 300

Text #7

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.8184. Min Act: -0.1700

Data Index: 4664664 (Open Web Text)

Max Activating Token Index: 394

Text #8

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.8008. Min Act: -0.1700

Data Index: 1790369 (Open Web Text)

Max Activating Token Index: 713

Text #9

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.7872. Min Act: -0.1700

Data Index: 8230721 (Open Web Text)

Max Activating Token Index: 738

Text #10

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.7780. Min Act: -0.1700

Data Index: 8682924 (Open Web Text)

Max Activating Token Index: 566

Text #11

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.7489. Min Act: -0.1700

Data Index: 2196768 (Open Web Text)

Max Activating Token Index: 216

Text #12

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.7541. Min Act: -0.1700

Data Index: 7192489 (Open Web Text)

Max Activating Token Index: 160

Text #13

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.7802. Min Act: -0.1700

Data Index: 360329 (Open Web Text)

Max Activating Token Index: 347

Text #14

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.7564. Min Act: -0.1700

Data Index: 4863450 (Open Web Text)

Max Activating Token Index: 605

Text #15

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.7863. Min Act: -0.1700

Data Index: 5345935 (Open Web Text)

Max Activating Token Index: 565

Text #16

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.7615. Min Act: -0.1700

Data Index: 1965216 (Open Web Text)

Max Activating Token Index: 650

Text #17

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.7598. Min Act: -0.1700

Data Index: 862385 (Open Web Text)

Max Activating Token Index: 685

Text #18

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.7480. Min Act: -0.1700

Data Index: 890845 (Open Web Text)

Max Activating Token Index: 315

Text #19

Max Range: 3.9498. Min Range: -3.9498

Max Act: 3.7793. Min Act: -0.1700

Data Index: 8023491 (Open Web Text)

Max Activating Token Index: 547