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

Dataset: Open Web Text

Neuron 901 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: 3.0468. Min Range: -3.0468

Max Act: 3.0468. Min Act: -0.1700

Data Index: 5383781 (Open Web Text)

Max Activating Token Index: 166

Text #1

Max Range: 3.0468. Min Range: -3.0468

Max Act: 3.0206. Min Act: -0.1700

Data Index: 1037218 (Open Web Text)

Max Activating Token Index: 507

Text #2

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.9856. Min Act: -0.1700

Data Index: 7869701 (Open Web Text)

Max Activating Token Index: 132

Text #3

Max Range: 3.0468. Min Range: -3.0468

Max Act: 3.0028. Min Act: -0.1700

Data Index: 6334715 (Open Web Text)

Max Activating Token Index: 238

Text #4

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.9773. Min Act: -0.1700

Data Index: 5072951 (Open Web Text)

Max Activating Token Index: 808

Text #5

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.9297. Min Act: -0.1700

Data Index: 7072333 (Open Web Text)

Max Activating Token Index: 791

Text #6

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.9039. Min Act: -0.1700

Data Index: 4097680 (Open Web Text)

Max Activating Token Index: 661

Text #7

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.9048. Min Act: -0.1700

Data Index: 1811475 (Open Web Text)

Max Activating Token Index: 955

Text #8

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.9145. Min Act: -0.1700

Data Index: 1312077 (Open Web Text)

Max Activating Token Index: 593

Text #9

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.9077. Min Act: -0.1700

Data Index: 2423212 (Open Web Text)

Max Activating Token Index: 489

Text #10

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.8964. Min Act: -0.1700

Data Index: 5791870 (Open Web Text)

Max Activating Token Index: 864

Text #11

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.8803. Min Act: -0.1700

Data Index: 6805585 (Open Web Text)

Max Activating Token Index: 849

Text #12

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.9069. Min Act: -0.1700

Data Index: 6735590 (Open Web Text)

Max Activating Token Index: 519

Text #13

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.9182. Min Act: -0.1700

Data Index: 6889991 (Open Web Text)

Max Activating Token Index: 168

Text #14

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.8870. Min Act: -0.1700

Data Index: 1833931 (Open Web Text)

Max Activating Token Index: 542

Text #15

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.8746. Min Act: -0.1700

Data Index: 3343710 (Open Web Text)

Max Activating Token Index: 338

Text #16

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.8586. Min Act: -0.1700

Data Index: 7968718 (Open Web Text)

Max Activating Token Index: 721

Text #17

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.8821. Min Act: -0.1700

Data Index: 4804345 (Open Web Text)

Max Activating Token Index: 828

Text #18

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.9038. Min Act: -0.1700

Data Index: 2090573 (Open Web Text)

Max Activating Token Index: 33

Text #19

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.8774. Min Act: -0.1700

Data Index: 5970812 (Open Web Text)

Max Activating Token Index: 324