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

Dataset: Open Web Text

Neuron 1324 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: 4.5621. Min Range: -4.5621

Max Act: 4.5621. Min Act: -0.1700

Data Index: 8007824 (Open Web Text)

Max Activating Token Index: 529

Text #1

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.4822. Min Act: -0.1700

Data Index: 8007820 (Open Web Text)

Max Activating Token Index: 303

Text #2

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.4142. Min Act: -0.1700

Data Index: 1172014 (Open Web Text)

Max Activating Token Index: 927

Text #3

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.3874. Min Act: -0.1700

Data Index: 4843573 (Open Web Text)

Max Activating Token Index: 592

Text #4

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.3933. Min Act: -0.1700

Data Index: 692516 (Open Web Text)

Max Activating Token Index: 202

Text #5

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.3340. Min Act: -0.1700

Data Index: 681080 (Open Web Text)

Max Activating Token Index: 36

Text #6

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.3137. Min Act: -0.1700

Data Index: 7929124 (Open Web Text)

Max Activating Token Index: 270

Text #7

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.3259. Min Act: -0.1700

Data Index: 6282273 (Open Web Text)

Max Activating Token Index: 1019

Text #8

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.2700. Min Act: -0.1700

Data Index: 1556414 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.2923. Min Act: -0.1700

Data Index: 4531017 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.2748. Min Act: -0.1700

Data Index: 6331564 (Open Web Text)

Max Activating Token Index: 546

Text #11

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.2912. Min Act: -0.1700

Data Index: 4801113 (Open Web Text)

Max Activating Token Index: 999

Text #12

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.2930. Min Act: -0.1700

Data Index: 6848288 (Open Web Text)

Max Activating Token Index: 552

Text #13

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.2640. Min Act: -0.1700

Data Index: 4922525 (Open Web Text)

Max Activating Token Index: 256

Text #14

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.2131. Min Act: -0.1700

Data Index: 7023014 (Open Web Text)

Max Activating Token Index: 1004

Text #15

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.1940. Min Act: -0.1700

Data Index: 1688518 (Open Web Text)

Max Activating Token Index: 100

Text #16

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.2229. Min Act: -0.1700

Data Index: 8394886 (Open Web Text)

Max Activating Token Index: 721

Text #17

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.2361. Min Act: -0.1700

Data Index: 4145365 (Open Web Text)

Max Activating Token Index: 916

Text #18

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.2089. Min Act: -0.1700

Data Index: 7778041 (Open Web Text)

Max Activating Token Index: 197

Text #19

Max Range: 4.5621. Min Range: -4.5621

Max Act: 4.1940. Min Act: -0.1700

Data Index: 6345755 (Open Web Text)

Max Activating Token Index: 686