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

Dataset: Open Web Text

Neuron 301 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: 2.4449. Min Range: -2.4449

Max Act: 2.4449. Min Act: -0.1700

Data Index: 7685489 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.4058. Min Act: -0.1700

Data Index: 5015913 (Open Web Text)

Max Activating Token Index: 463

Text #2

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.4205. Min Act: -0.1700

Data Index: 1256831 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.4217. Min Act: -0.1700

Data Index: 6205551 (Open Web Text)

Max Activating Token Index: 755

Text #4

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3810. Min Act: -0.1700

Data Index: 5546072 (Open Web Text)

Max Activating Token Index: 353

Text #5

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3922. Min Act: -0.1700

Data Index: 253973 (Open Web Text)

Max Activating Token Index: 408

Text #6

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3755. Min Act: -0.1700

Data Index: 3917138 (Open Web Text)

Max Activating Token Index: 537

Text #7

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3862. Min Act: -0.1700

Data Index: 3780732 (Open Web Text)

Max Activating Token Index: 605

Text #8

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3698. Min Act: -0.1700

Data Index: 6241659 (Open Web Text)

Max Activating Token Index: 332

Text #9

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3841. Min Act: -0.1700

Data Index: 8007007 (Open Web Text)

Max Activating Token Index: 454

Text #10

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3577. Min Act: -0.1700

Data Index: 5038845 (Open Web Text)

Max Activating Token Index: 633

Text #11

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3504. Min Act: -0.1700

Data Index: 1614334 (Open Web Text)

Max Activating Token Index: 264

Text #12

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3390. Min Act: -0.1700

Data Index: 2942095 (Open Web Text)

Max Activating Token Index: 575

Text #13

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3399. Min Act: -0.1700

Data Index: 948026 (Open Web Text)

Max Activating Token Index: 507

Text #14

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3634. Min Act: -0.1700

Data Index: 6546020 (Open Web Text)

Max Activating Token Index: 728

Text #15

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3541. Min Act: -0.1700

Data Index: 3422434 (Open Web Text)

Max Activating Token Index: 674

Text #16

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3466. Min Act: -0.1700

Data Index: 49677 (Open Web Text)

Max Activating Token Index: 763

Text #17

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3483. Min Act: -0.1700

Data Index: 6642741 (Open Web Text)

Max Activating Token Index: 674

Text #18

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3342. Min Act: -0.1700

Data Index: 3749389 (Open Web Text)

Max Activating Token Index: 467

Text #19

Max Range: 2.4449. Min Range: -2.4449

Max Act: 2.3420. Min Act: -0.1700

Data Index: 655924 (Open Web Text)

Max Activating Token Index: 201