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

Dataset: Open Web Text

Neuron 2017 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: 4.7816. Min Range: -4.7816

Max Act: 4.7816. Min Act: -0.1700

Data Index: 7385697 (Open Web Text)

Max Activating Token Index: 572

Text #1

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.7605. Min Act: -0.1700

Data Index: 6331257 (Open Web Text)

Max Activating Token Index: 529

Text #2

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.6665. Min Act: -0.1700

Data Index: 1409454 (Open Web Text)

Max Activating Token Index: 250

Text #3

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.5991. Min Act: -0.1700

Data Index: 1409136 (Open Web Text)

Max Activating Token Index: 686

Text #4

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.6085. Min Act: -0.1700

Data Index: 5759455 (Open Web Text)

Max Activating Token Index: 366

Text #5

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.5993. Min Act: -0.1700

Data Index: 539267 (Open Web Text)

Max Activating Token Index: 544

Text #6

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.6047. Min Act: -0.1700

Data Index: 6472804 (Open Web Text)

Max Activating Token Index: 675

Text #7

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.5894. Min Act: -0.1700

Data Index: 5673573 (Open Web Text)

Max Activating Token Index: 191

Text #8

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.6053. Min Act: -0.1700

Data Index: 6914336 (Open Web Text)

Max Activating Token Index: 486

Text #9

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.5847. Min Act: -0.1700

Data Index: 2653868 (Open Web Text)

Max Activating Token Index: 857

Text #10

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.5493. Min Act: -0.1700

Data Index: 5971653 (Open Web Text)

Max Activating Token Index: 740

Text #11

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.5637. Min Act: -0.1700

Data Index: 5135382 (Open Web Text)

Max Activating Token Index: 418

Text #12

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.5364. Min Act: -0.1700

Data Index: 5633394 (Open Web Text)

Max Activating Token Index: 460

Text #13

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.4798. Min Act: -0.1700

Data Index: 6969804 (Open Web Text)

Max Activating Token Index: 248

Text #14

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.5001. Min Act: -0.1700

Data Index: 2223689 (Open Web Text)

Max Activating Token Index: 341

Text #15

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.4860. Min Act: -0.1700

Data Index: 3750572 (Open Web Text)

Max Activating Token Index: 754

Text #16

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.4870. Min Act: -0.1700

Data Index: 3504492 (Open Web Text)

Max Activating Token Index: 756

Text #17

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.4572. Min Act: -0.1700

Data Index: 8309524 (Open Web Text)

Max Activating Token Index: 799

Text #18

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.5107. Min Act: -0.1700

Data Index: 7576765 (Open Web Text)

Max Activating Token Index: 793

Text #19

Max Range: 4.7816. Min Range: -4.7816

Max Act: 4.4387. Min Act: -0.1700

Data Index: 6611533 (Open Web Text)

Max Activating Token Index: 111