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

Dataset: Open Web Text

Neuron 1421 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: 3.7837. Min Range: -3.7837

Max Act: 3.7837. Min Act: -0.1700

Data Index: 5722269 (Open Web Text)

Max Activating Token Index: 381

Text #1

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.6278. Min Act: -0.1700

Data Index: 683094 (Open Web Text)

Max Activating Token Index: 510

Text #2

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.6194. Min Act: -0.1700

Data Index: 745789 (Open Web Text)

Max Activating Token Index: 188

Text #3

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.5329. Min Act: -0.1700

Data Index: 3231381 (Open Web Text)

Max Activating Token Index: 958

Text #4

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.4844. Min Act: -0.1700

Data Index: 4382613 (Open Web Text)

Max Activating Token Index: 918

Text #5

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.4918. Min Act: -0.1700

Data Index: 6419856 (Open Web Text)

Max Activating Token Index: 670

Text #6

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.5700. Min Act: -0.1700

Data Index: 3209131 (Open Web Text)

Max Activating Token Index: 481

Text #7

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.4695. Min Act: -0.1700

Data Index: 7573123 (Open Web Text)

Max Activating Token Index: 332

Text #8

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.5032. Min Act: -0.1700

Data Index: 2691629 (Open Web Text)

Max Activating Token Index: 567

Text #9

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.4767. Min Act: -0.1700

Data Index: 354218 (Open Web Text)

Max Activating Token Index: 639

Text #10

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.4614. Min Act: -0.1700

Data Index: 5405906 (Open Web Text)

Max Activating Token Index: 511

Text #11

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.5078. Min Act: -0.1700

Data Index: 5665364 (Open Web Text)

Max Activating Token Index: 201

Text #12

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.4639. Min Act: -0.1700

Data Index: 5492842 (Open Web Text)

Max Activating Token Index: 766

Text #13

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.4982. Min Act: -0.1700

Data Index: 808434 (Open Web Text)

Max Activating Token Index: 155

Text #14

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.4341. Min Act: -0.1700

Data Index: 2196740 (Open Web Text)

Max Activating Token Index: 434

Text #15

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.4729. Min Act: -0.1700

Data Index: 3739881 (Open Web Text)

Max Activating Token Index: 884

Text #16

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.4322. Min Act: -0.1700

Data Index: 3638675 (Open Web Text)

Max Activating Token Index: 143

Text #17

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.4585. Min Act: -0.1700

Data Index: 2212290 (Open Web Text)

Max Activating Token Index: 1001

Text #18

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.4324. Min Act: -0.1700

Data Index: 904491 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.4477. Min Act: -0.1700

Data Index: 2210428 (Open Web Text)

Max Activating Token Index: 258