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

Dataset: Open Web Text

Neuron 2579 in Layer 1

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: 5.0393. Min Range: -5.0393

Max Act: 5.0393. Min Act: -0.1700

Data Index: 894587 (Open Web Text)

Max Activating Token Index: 181

Text #1

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.9995. Min Act: -0.1700

Data Index: 6762566 (Open Web Text)

Max Activating Token Index: 492

Text #2

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.9883. Min Act: -0.1700

Data Index: 5397310 (Open Web Text)

Max Activating Token Index: 1006

Text #3

Max Range: 5.0393. Min Range: -5.0393

Max Act: 5.0064. Min Act: -0.1700

Data Index: 2899292 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 5.0393. Min Range: -5.0393

Max Act: 5.0011. Min Act: -0.1700

Data Index: 8826997 (Open Web Text)

Max Activating Token Index: 543

Text #5

Max Range: 5.0393. Min Range: -5.0393

Max Act: 5.0369. Min Act: -0.1700

Data Index: 4101199 (Open Web Text)

Max Activating Token Index: 633

Text #6

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.9813. Min Act: -0.1700

Data Index: 8299362 (Open Web Text)

Max Activating Token Index: 597

Text #7

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.9586. Min Act: -0.1700

Data Index: 5815893 (Open Web Text)

Max Activating Token Index: 196

Text #8

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.9381. Min Act: -0.1700

Data Index: 3315334 (Open Web Text)

Max Activating Token Index: 544

Text #9

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.9333. Min Act: -0.1700

Data Index: 3174911 (Open Web Text)

Max Activating Token Index: 129

Text #10

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.9199. Min Act: -0.1700

Data Index: 6481316 (Open Web Text)

Max Activating Token Index: 675

Text #11

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.9117. Min Act: -0.1700

Data Index: 5376560 (Open Web Text)

Max Activating Token Index: 810

Text #12

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.9103. Min Act: -0.1700

Data Index: 7930715 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.8890. Min Act: -0.1700

Data Index: 4919671 (Open Web Text)

Max Activating Token Index: 403

Text #14

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.8899. Min Act: -0.1700

Data Index: 2925974 (Open Web Text)

Max Activating Token Index: 595

Text #15

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.8636. Min Act: -0.1700

Data Index: 5981240 (Open Web Text)

Max Activating Token Index: 1019

Text #16

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.8918. Min Act: -0.1700

Data Index: 3095928 (Open Web Text)

Max Activating Token Index: 537

Text #17

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.8948. Min Act: -0.1700

Data Index: 1732602 (Open Web Text)

Max Activating Token Index: 627

Text #18

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.8717. Min Act: -0.1700

Data Index: 3143166 (Open Web Text)

Max Activating Token Index: 478

Text #19

Max Range: 5.0393. Min Range: -5.0393

Max Act: 4.8694. Min Act: -0.1700

Data Index: 6122688 (Open Web Text)

Max Activating Token Index: 368