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

Dataset: Open Web Text

Neuron 2644 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: 1.5486. Min Range: -1.5486

Max Act: 1.5486. Min Act: -0.1700

Data Index: 3912506 (Open Web Text)

Max Activating Token Index: 446

Text #1

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.5299. Min Act: -0.1700

Data Index: 8062589 (Open Web Text)

Max Activating Token Index: 855

Text #2

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.5451. Min Act: -0.1700

Data Index: 5090877 (Open Web Text)

Max Activating Token Index: 320

Text #3

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.5299. Min Act: -0.1700

Data Index: 3777855 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.5058. Min Act: -0.1700

Data Index: 1593186 (Open Web Text)

Max Activating Token Index: 657

Text #5

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.5056. Min Act: -0.1700

Data Index: 1250586 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.5038. Min Act: -0.1700

Data Index: 2939936 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.4934. Min Act: -0.1700

Data Index: 2485745 (Open Web Text)

Max Activating Token Index: 747

Text #8

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.4951. Min Act: -0.1700

Data Index: 3469460 (Open Web Text)

Max Activating Token Index: 160

Text #9

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.4726. Min Act: -0.1700

Data Index: 8379242 (Open Web Text)

Max Activating Token Index: 690

Text #10

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.4851. Min Act: -0.1700

Data Index: 6823440 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.4689. Min Act: -0.1700

Data Index: 3082044 (Open Web Text)

Max Activating Token Index: 132

Text #12

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.4710. Min Act: -0.1700

Data Index: 6431604 (Open Web Text)

Max Activating Token Index: 267

Text #13

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.4734. Min Act: -0.1700

Data Index: 2052741 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.4555. Min Act: -0.1700

Data Index: 5069549 (Open Web Text)

Max Activating Token Index: 402

Text #15

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.4696. Min Act: -0.1700

Data Index: 2972432 (Open Web Text)

Max Activating Token Index: 558

Text #16

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.4577. Min Act: -0.1700

Data Index: 4538803 (Open Web Text)

Max Activating Token Index: 284

Text #17

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.4394. Min Act: -0.1699

Data Index: 4062432 (Open Web Text)

Max Activating Token Index: 507

Text #18

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.4436. Min Act: -0.1700

Data Index: 7646066 (Open Web Text)

Max Activating Token Index: 571

Text #19

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.4359. Min Act: -0.1700

Data Index: 7214440 (Open Web Text)

Max Activating Token Index: 1003