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

Dataset: Open Web Text

Neuron 578 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: 4.3315. Min Range: -4.3315

Max Act: 4.3315. Min Act: -0.1700

Data Index: 971240 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 4.3315. Min Range: -4.3315

Max Act: 4.2573. Min Act: -0.1700

Data Index: 5025290 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.3315. Min Range: -4.3315

Max Act: 4.1711. Min Act: -0.1700

Data Index: 8275705 (Open Web Text)

Max Activating Token Index: 488

Text #3

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.9455. Min Act: -0.1700

Data Index: 7987192 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.7984. Min Act: -0.1700

Data Index: 4391169 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.7691. Min Act: -0.1700

Data Index: 7439079 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.7108. Min Act: -0.1700

Data Index: 3488233 (Open Web Text)

Max Activating Token Index: 608

Text #7

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.7008. Min Act: -0.1700

Data Index: 5066693 (Open Web Text)

Max Activating Token Index: 22

Text #8

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.6898. Min Act: -0.1700

Data Index: 8001107 (Open Web Text)

Max Activating Token Index: 283

Text #9

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.6490. Min Act: -0.1700

Data Index: 8065868 (Open Web Text)

Max Activating Token Index: 35

Text #10

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.6211. Min Act: -0.1700

Data Index: 8541530 (Open Web Text)

Max Activating Token Index: 123

Text #11

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.5791. Min Act: -0.1700

Data Index: 7542204 (Open Web Text)

Max Activating Token Index: 570

Text #12

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.5114. Min Act: -0.1700

Data Index: 1928085 (Open Web Text)

Max Activating Token Index: 217

Text #13

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.5104. Min Act: -0.1700

Data Index: 3690496 (Open Web Text)

Max Activating Token Index: 25

Text #14

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.5010. Min Act: -0.1700

Data Index: 40715 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.5097. Min Act: -0.1700

Data Index: 235478 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.4683. Min Act: -0.1700

Data Index: 3728129 (Open Web Text)

Max Activating Token Index: 31

Text #17

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.4807. Min Act: -0.1700

Data Index: 7033659 (Open Web Text)

Max Activating Token Index: 78

Text #18

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.5017. Min Act: -0.1700

Data Index: 7124525 (Open Web Text)

Max Activating Token Index: 545

Text #19

Max Range: 4.3315. Min Range: -4.3315

Max Act: 3.4575. Min Act: -0.1700

Data Index: 4581142 (Open Web Text)

Max Activating Token Index: 499