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

Dataset: Open Web Text

Neuron 527 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: 3.5005. Min Range: -3.5005

Max Act: 3.5005. Min Act: -0.1700

Data Index: 7669499 (Open Web Text)

Max Activating Token Index: 64

Text #1

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.4369. Min Act: -0.1700

Data Index: 1989844 (Open Web Text)

Max Activating Token Index: 790

Text #2

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.4391. Min Act: -0.1700

Data Index: 224475 (Open Web Text)

Max Activating Token Index: 633

Text #3

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.4103. Min Act: -0.1700

Data Index: 6173751 (Open Web Text)

Max Activating Token Index: 314

Text #4

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3860. Min Act: -0.1700

Data Index: 5172508 (Open Web Text)

Max Activating Token Index: 243

Text #5

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3706. Min Act: -0.1700

Data Index: 3933806 (Open Web Text)

Max Activating Token Index: 548

Text #6

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3620. Min Act: -0.1700

Data Index: 439196 (Open Web Text)

Max Activating Token Index: 268

Text #7

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3395. Min Act: -0.1700

Data Index: 7365763 (Open Web Text)

Max Activating Token Index: 796

Text #8

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3428. Min Act: -0.1700

Data Index: 891572 (Open Web Text)

Max Activating Token Index: 539

Text #9

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3462. Min Act: -0.1700

Data Index: 6656237 (Open Web Text)

Max Activating Token Index: 895

Text #10

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3538. Min Act: -0.1700

Data Index: 7920985 (Open Web Text)

Max Activating Token Index: 374

Text #11

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3526. Min Act: -0.1700

Data Index: 4260987 (Open Web Text)

Max Activating Token Index: 474

Text #12

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3531. Min Act: -0.1700

Data Index: 7928287 (Open Web Text)

Max Activating Token Index: 757

Text #13

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3466. Min Act: -0.1700

Data Index: 6364911 (Open Web Text)

Max Activating Token Index: 909

Text #14

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3259. Min Act: -0.1700

Data Index: 7401467 (Open Web Text)

Max Activating Token Index: 418

Text #15

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3394. Min Act: -0.1700

Data Index: 4987313 (Open Web Text)

Max Activating Token Index: 695

Text #16

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3381. Min Act: -0.1700

Data Index: 3572010 (Open Web Text)

Max Activating Token Index: 955

Text #17

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3272. Min Act: -0.1700

Data Index: 8029555 (Open Web Text)

Max Activating Token Index: 571

Text #18

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3261. Min Act: -0.1700

Data Index: 6319461 (Open Web Text)

Max Activating Token Index: 489

Text #19

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3350. Min Act: -0.1700

Data Index: 44056 (Open Web Text)

Max Activating Token Index: 563