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

Dataset: Open Web Text

Neuron 2019 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: 3.1220. Min Range: -3.1220

Max Act: 3.1220. Min Act: -0.1700

Data Index: 5651561 (Open Web Text)

Max Activating Token Index: 499

Text #1

Max Range: 3.1220. Min Range: -3.1220

Max Act: 3.0624. Min Act: -0.1700

Data Index: 4955231 (Open Web Text)

Max Activating Token Index: 110

Text #2

Max Range: 3.1220. Min Range: -3.1220

Max Act: 3.0631. Min Act: -0.1700

Data Index: 267761 (Open Web Text)

Max Activating Token Index: 141

Text #3

Max Range: 3.1220. Min Range: -3.1220

Max Act: 3.0503. Min Act: -0.1700

Data Index: 3904026 (Open Web Text)

Max Activating Token Index: 232

Text #4

Max Range: 3.1220. Min Range: -3.1220

Max Act: 3.0327. Min Act: -0.1700

Data Index: 3924904 (Open Web Text)

Max Activating Token Index: 247

Text #5

Max Range: 3.1220. Min Range: -3.1220

Max Act: 2.9920. Min Act: -0.1700

Data Index: 778201 (Open Web Text)

Max Activating Token Index: 543

Text #6

Max Range: 3.1220. Min Range: -3.1220

Max Act: 2.9947. Min Act: -0.1700

Data Index: 5946668 (Open Web Text)

Max Activating Token Index: 62

Text #7

Max Range: 3.1220. Min Range: -3.1220

Max Act: 2.9982. Min Act: -0.1700

Data Index: 1910188 (Open Web Text)

Max Activating Token Index: 945

Text #8

Max Range: 3.1220. Min Range: -3.1220

Max Act: 2.9764. Min Act: -0.1700

Data Index: 8443036 (Open Web Text)

Max Activating Token Index: 642

Text #9

Max Range: 3.1220. Min Range: -3.1220

Max Act: 2.9943. Min Act: -0.1700

Data Index: 3374709 (Open Web Text)

Max Activating Token Index: 573

Text #10

Max Range: 3.1220. Min Range: -3.1220

Max Act: 2.9596. Min Act: -0.1700

Data Index: 5603798 (Open Web Text)

Max Activating Token Index: 223

Text #11

Max Range: 3.1220. Min Range: -3.1220

Max Act: 2.9590. Min Act: -0.1700

Data Index: 3499364 (Open Web Text)

Max Activating Token Index: 550

Text #12

Max Range: 3.1220. Min Range: -3.1220

Max Act: 2.9755. Min Act: -0.1700

Data Index: 4446334 (Open Web Text)

Max Activating Token Index: 33

Text #13

Max Range: 3.1220. Min Range: -3.1220

Max Act: 2.9411. Min Act: -0.1700

Data Index: 487399 (Open Web Text)

Max Activating Token Index: 461

Text #14

Max Range: 3.1220. Min Range: -3.1220

Max Act: 2.9606. Min Act: -0.1700

Data Index: 5494629 (Open Web Text)

Max Activating Token Index: 664

Text #15

Max Range: 3.1220. Min Range: -3.1220

Max Act: 2.9418. Min Act: -0.1700

Data Index: 3224168 (Open Web Text)

Max Activating Token Index: 194

Text #16

Max Range: 3.1220. Min Range: -3.1220

Max Act: 2.9453. Min Act: -0.1700

Data Index: 1717894 (Open Web Text)

Max Activating Token Index: 756

Text #17

Max Range: 3.1220. Min Range: -3.1220

Max Act: 2.9501. Min Act: -0.1700

Data Index: 586732 (Open Web Text)

Max Activating Token Index: 120

Text #18

Max Range: 3.1220. Min Range: -3.1220

Max Act: 2.9423. Min Act: -0.1700

Data Index: 4052367 (Open Web Text)

Max Activating Token Index: 103

Text #19

Max Range: 3.1220. Min Range: -3.1220

Max Act: 2.9375. Min Act: -0.1700

Data Index: 3799006 (Open Web Text)

Max Activating Token Index: 742