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

Dataset: Open Web Text

Neuron 845 in Layer 3

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: 3.7272. Min Range: -3.7272

Max Act: 3.7272. Min Act: -0.1700

Data Index: 4371823 (Open Web Text)

Max Activating Token Index: 690

Text #1

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.7161. Min Act: -0.1700

Data Index: 6923739 (Open Web Text)

Max Activating Token Index: 913

Text #2

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.6322. Min Act: -0.1700

Data Index: 3086187 (Open Web Text)

Max Activating Token Index: 865

Text #3

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.6155. Min Act: -0.1700

Data Index: 2719445 (Open Web Text)

Max Activating Token Index: 905

Text #4

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.6155. Min Act: -0.1700

Data Index: 1403010 (Open Web Text)

Max Activating Token Index: 247

Text #5

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.6334. Min Act: -0.1700

Data Index: 11020 (Open Web Text)

Max Activating Token Index: 396

Text #6

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.5828. Min Act: -0.1700

Data Index: 978281 (Open Web Text)

Max Activating Token Index: 378

Text #7

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.5840. Min Act: -0.1700

Data Index: 2178583 (Open Web Text)

Max Activating Token Index: 576

Text #8

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.6011. Min Act: -0.1700

Data Index: 7160024 (Open Web Text)

Max Activating Token Index: 273

Text #9

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.6058. Min Act: -0.1700

Data Index: 2171099 (Open Web Text)

Max Activating Token Index: 729

Text #10

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.5771. Min Act: -0.1700

Data Index: 4894445 (Open Web Text)

Max Activating Token Index: 597

Text #11

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.5892. Min Act: -0.1700

Data Index: 3245648 (Open Web Text)

Max Activating Token Index: 205

Text #12

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.5711. Min Act: -0.1700

Data Index: 1217489 (Open Web Text)

Max Activating Token Index: 945

Text #13

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.6101. Min Act: -0.1700

Data Index: 6718504 (Open Web Text)

Max Activating Token Index: 150

Text #14

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.5981. Min Act: -0.1700

Data Index: 6844971 (Open Web Text)

Max Activating Token Index: 190

Text #15

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.6108. Min Act: -0.1700

Data Index: 3825173 (Open Web Text)

Max Activating Token Index: 752

Text #16

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.5788. Min Act: -0.1700

Data Index: 3438544 (Open Web Text)

Max Activating Token Index: 168

Text #17

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.5845. Min Act: -0.1700

Data Index: 4965556 (Open Web Text)

Max Activating Token Index: 515

Text #18

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.5825. Min Act: -0.1700

Data Index: 6121358 (Open Web Text)

Max Activating Token Index: 904

Text #19

Max Range: 3.7272. Min Range: -3.7272

Max Act: 3.5693. Min Act: -0.1700

Data Index: 4595779 (Open Web Text)

Max Activating Token Index: 727