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

Dataset: Open Web Text

Neuron 1571 in Layer 2

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: 1.6984. Min Range: -1.6984

Max Act: 1.6984. Min Act: -0.1700

Data Index: 1397376 (Open Web Text)

Max Activating Token Index: 985

Text #1

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6733. Min Act: -0.1700

Data Index: 2658795 (Open Web Text)

Max Activating Token Index: 377

Text #2

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6626. Min Act: -0.1700

Data Index: 7918159 (Open Web Text)

Max Activating Token Index: 462

Text #3

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6659. Min Act: -0.1700

Data Index: 4496014 (Open Web Text)

Max Activating Token Index: 51

Text #4

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6675. Min Act: -0.1700

Data Index: 3182748 (Open Web Text)

Max Activating Token Index: 576

Text #5

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6658. Min Act: -0.1700

Data Index: 8488612 (Open Web Text)

Max Activating Token Index: 441

Text #6

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6481. Min Act: -0.1700

Data Index: 5910894 (Open Web Text)

Max Activating Token Index: 641

Text #7

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6477. Min Act: -0.1700

Data Index: 2366744 (Open Web Text)

Max Activating Token Index: 663

Text #8

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6530. Min Act: -0.1700

Data Index: 1981514 (Open Web Text)

Max Activating Token Index: 472

Text #9

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6531. Min Act: -0.1700

Data Index: 2633734 (Open Web Text)

Max Activating Token Index: 535

Text #10

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6418. Min Act: -0.1700

Data Index: 2509818 (Open Web Text)

Max Activating Token Index: 548

Text #11

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6458. Min Act: -0.1700

Data Index: 4066385 (Open Web Text)

Max Activating Token Index: 53

Text #12

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6376. Min Act: -0.1700

Data Index: 8436600 (Open Web Text)

Max Activating Token Index: 129

Text #13

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6538. Min Act: -0.1699

Data Index: 8663613 (Open Web Text)

Max Activating Token Index: 195

Text #14

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6509. Min Act: -0.1698

Data Index: 1328060 (Open Web Text)

Max Activating Token Index: 881

Text #15

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6387. Min Act: -0.1700

Data Index: 3179070 (Open Web Text)

Max Activating Token Index: 452

Text #16

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6282. Min Act: -0.1699

Data Index: 4542609 (Open Web Text)

Max Activating Token Index: 495

Text #17

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6463. Min Act: -0.1700

Data Index: 1628335 (Open Web Text)

Max Activating Token Index: 534

Text #18

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6467. Min Act: -0.1700

Data Index: 1660418 (Open Web Text)

Max Activating Token Index: 531

Text #19

Max Range: 1.6984. Min Range: -1.6984

Max Act: 1.6375. Min Act: -0.1700

Data Index: 2421942 (Open Web Text)

Max Activating Token Index: 46