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

Dataset: Open Web Text

Neuron 1780 in Layer 4

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: 3.4613. Min Range: -3.4613

Max Act: 3.4613. Min Act: -0.1700

Data Index: 3252033 (Open Web Text)

Max Activating Token Index: 591

Text #1

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.3881. Min Act: -0.1700

Data Index: 6606947 (Open Web Text)

Max Activating Token Index: 597

Text #2

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.3578. Min Act: -0.1700

Data Index: 7972659 (Open Web Text)

Max Activating Token Index: 567

Text #3

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.3051. Min Act: -0.1700

Data Index: 508833 (Open Web Text)

Max Activating Token Index: 379

Text #4

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.3093. Min Act: -0.1700

Data Index: 7749722 (Open Web Text)

Max Activating Token Index: 805

Text #5

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.2619. Min Act: -0.1700

Data Index: 8669904 (Open Web Text)

Max Activating Token Index: 718

Text #6

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.2615. Min Act: -0.1700

Data Index: 8227475 (Open Web Text)

Max Activating Token Index: 227

Text #7

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.2076. Min Act: -0.1700

Data Index: 1592429 (Open Web Text)

Max Activating Token Index: 448

Text #8

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.2444. Min Act: -0.1700

Data Index: 1360493 (Open Web Text)

Max Activating Token Index: 82

Text #9

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.2125. Min Act: -0.1700

Data Index: 530086 (Open Web Text)

Max Activating Token Index: 1010

Text #10

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.2091. Min Act: -0.1700

Data Index: 149983 (Open Web Text)

Max Activating Token Index: 410

Text #11

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1904. Min Act: -0.1700

Data Index: 3827036 (Open Web Text)

Max Activating Token Index: 118

Text #12

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1973. Min Act: -0.1700

Data Index: 4428422 (Open Web Text)

Max Activating Token Index: 232

Text #13

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.2346. Min Act: -0.1700

Data Index: 3606689 (Open Web Text)

Max Activating Token Index: 416

Text #14

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.2102. Min Act: -0.1700

Data Index: 8241376 (Open Web Text)

Max Activating Token Index: 557

Text #15

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1999. Min Act: -0.1700

Data Index: 3827037 (Open Web Text)

Max Activating Token Index: 351

Text #16

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1967. Min Act: -0.1700

Data Index: 3209644 (Open Web Text)

Max Activating Token Index: 145

Text #17

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1928. Min Act: -0.1700

Data Index: 6455176 (Open Web Text)

Max Activating Token Index: 590

Text #18

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1840. Min Act: -0.1700

Data Index: 8689828 (Open Web Text)

Max Activating Token Index: 701

Text #19

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1848. Min Act: -0.1700

Data Index: 4799513 (Open Web Text)

Max Activating Token Index: 101