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

Dataset: Open Web Text

Neuron 414 in Layer 0

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: 3.5353. Min Range: -3.5353

Max Act: 3.5353. Min Act: -0.1700

Data Index: 2569431 (Open Web Text)

Max Activating Token Index: 712

Text #1

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.5054. Min Act: -0.1700

Data Index: 3449242 (Open Web Text)

Max Activating Token Index: 293

Text #2

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.4876. Min Act: -0.1700

Data Index: 7701309 (Open Web Text)

Max Activating Token Index: 429

Text #3

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.4382. Min Act: -0.1700

Data Index: 7108893 (Open Web Text)

Max Activating Token Index: 961

Text #4

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.4613. Min Act: -0.1700

Data Index: 6474985 (Open Web Text)

Max Activating Token Index: 99

Text #5

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.4513. Min Act: -0.1700

Data Index: 3984232 (Open Web Text)

Max Activating Token Index: 439

Text #6

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.4345. Min Act: -0.1700

Data Index: 8435656 (Open Web Text)

Max Activating Token Index: 395

Text #7

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.4421. Min Act: -0.1700

Data Index: 8640700 (Open Web Text)

Max Activating Token Index: 438

Text #8

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.4478. Min Act: -0.1700

Data Index: 4802900 (Open Web Text)

Max Activating Token Index: 742

Text #9

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.4024. Min Act: -0.1700

Data Index: 6584267 (Open Web Text)

Max Activating Token Index: 545

Text #10

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.3912. Min Act: -0.1700

Data Index: 6125781 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.4023. Min Act: -0.1700

Data Index: 53175 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.4202. Min Act: -0.1700

Data Index: 5649241 (Open Web Text)

Max Activating Token Index: 700

Text #13

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.4141. Min Act: -0.1700

Data Index: 5647580 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.4066. Min Act: -0.1700

Data Index: 7129643 (Open Web Text)

Max Activating Token Index: 332

Text #15

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.3690. Min Act: -0.1700

Data Index: 7240700 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.3712. Min Act: -0.1700

Data Index: 7573008 (Open Web Text)

Max Activating Token Index: 550

Text #17

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.3764. Min Act: -0.1700

Data Index: 2703602 (Open Web Text)

Max Activating Token Index: 261

Text #18

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.3768. Min Act: -0.1700

Data Index: 1688811 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.5353. Min Range: -3.5353

Max Act: 3.3768. Min Act: -0.1700

Data Index: 4983429 (Open Web Text)

Max Activating Token Index: 161