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

Dataset: Open Web Text

Neuron 603 in Layer 3

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: 3.3294. Min Range: -3.3294

Max Act: 3.3294. Min Act: -0.1700

Data Index: 4235565 (Open Web Text)

Max Activating Token Index: 970

Text #1

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.3083. Min Act: -0.1700

Data Index: 448797 (Open Web Text)

Max Activating Token Index: 743

Text #2

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.3040. Min Act: -0.1700

Data Index: 4013841 (Open Web Text)

Max Activating Token Index: 431

Text #3

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.3085. Min Act: -0.1700

Data Index: 8399546 (Open Web Text)

Max Activating Token Index: 466

Text #4

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2749. Min Act: -0.1700

Data Index: 3789045 (Open Web Text)

Max Activating Token Index: 617

Text #5

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2463. Min Act: -0.1700

Data Index: 7884163 (Open Web Text)

Max Activating Token Index: 348

Text #6

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2437. Min Act: -0.1700

Data Index: 3354644 (Open Web Text)

Max Activating Token Index: 800

Text #7

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2480. Min Act: -0.1700

Data Index: 8770956 (Open Web Text)

Max Activating Token Index: 362

Text #8

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2246. Min Act: -0.1700

Data Index: 3329496 (Open Web Text)

Max Activating Token Index: 416

Text #9

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2080. Min Act: -0.1700

Data Index: 2518512 (Open Web Text)

Max Activating Token Index: 609

Text #10

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2456. Min Act: -0.1700

Data Index: 444992 (Open Web Text)

Max Activating Token Index: 747

Text #11

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.1968. Min Act: -0.1700

Data Index: 582654 (Open Web Text)

Max Activating Token Index: 496

Text #12

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.1841. Min Act: -0.1700

Data Index: 8679964 (Open Web Text)

Max Activating Token Index: 968

Text #13

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2257. Min Act: -0.1700

Data Index: 6115495 (Open Web Text)

Max Activating Token Index: 971

Text #14

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.1905. Min Act: -0.1700

Data Index: 2625348 (Open Web Text)

Max Activating Token Index: 366

Text #15

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.1986. Min Act: -0.1700

Data Index: 7774576 (Open Web Text)

Max Activating Token Index: 753

Text #16

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.1778. Min Act: -0.1700

Data Index: 4413666 (Open Web Text)

Max Activating Token Index: 31

Text #17

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.1752. Min Act: -0.1700

Data Index: 6055368 (Open Web Text)

Max Activating Token Index: 737

Text #18

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2172. Min Act: -0.1700

Data Index: 5189464 (Open Web Text)

Max Activating Token Index: 636

Text #19

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.1789. Min Act: -0.1700

Data Index: 4221963 (Open Web Text)

Max Activating Token Index: 317