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

Dataset: Open Web Text

Neuron 1800 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: 4.3520. Min Range: -4.3520

Max Act: 4.3501. Min Act: -0.1700

Data Index: 4363759 (Open Web Text)

Max Activating Token Index: 1001

Text #1

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.3520. Min Act: -0.1700

Data Index: 1185716 (Open Web Text)

Max Activating Token Index: 682

Text #2

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.2790. Min Act: -0.1700

Data Index: 8089955 (Open Web Text)

Max Activating Token Index: 320

Text #3

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.3014. Min Act: -0.1700

Data Index: 2423789 (Open Web Text)

Max Activating Token Index: 501

Text #4

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.2410. Min Act: -0.1700

Data Index: 4949527 (Open Web Text)

Max Activating Token Index: 444

Text #5

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.2445. Min Act: -0.1700

Data Index: 5260272 (Open Web Text)

Max Activating Token Index: 384

Text #6

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.2464. Min Act: -0.1700

Data Index: 3580546 (Open Web Text)

Max Activating Token Index: 242

Text #7

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.2804. Min Act: -0.1700

Data Index: 304652 (Open Web Text)

Max Activating Token Index: 947

Text #8

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.2716. Min Act: -0.1700

Data Index: 5321327 (Open Web Text)

Max Activating Token Index: 979

Text #9

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.2135. Min Act: -0.1700

Data Index: 7135347 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.1873. Min Act: -0.1700

Data Index: 528405 (Open Web Text)

Max Activating Token Index: 730

Text #11

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.1836. Min Act: -0.1700

Data Index: 7526609 (Open Web Text)

Max Activating Token Index: 681

Text #12

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.1956. Min Act: -0.1700

Data Index: 4769079 (Open Web Text)

Max Activating Token Index: 719

Text #13

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.2192. Min Act: -0.1700

Data Index: 6753512 (Open Web Text)

Max Activating Token Index: 575

Text #14

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.2242. Min Act: -0.1700

Data Index: 661961 (Open Web Text)

Max Activating Token Index: 779

Text #15

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.2065. Min Act: -0.1700

Data Index: 661954 (Open Web Text)

Max Activating Token Index: 668

Text #16

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.2049. Min Act: -0.1700

Data Index: 4208797 (Open Web Text)

Max Activating Token Index: 124

Text #17

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.1942. Min Act: -0.1700

Data Index: 4179453 (Open Web Text)

Max Activating Token Index: 890

Text #18

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.1799. Min Act: -0.1700

Data Index: 3565650 (Open Web Text)

Max Activating Token Index: 395

Text #19

Max Range: 4.3520. Min Range: -4.3520

Max Act: 4.1726. Min Act: -0.1700

Data Index: 1312468 (Open Web Text)

Max Activating Token Index: 579