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

Dataset: Open Web Text

Neuron 1478 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: 4.6984. Min Range: -4.6984

Max Act: 4.6984. Min Act: -0.1700

Data Index: 1606729 (Open Web Text)

Max Activating Token Index: 138

Text #1

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.6442. Min Act: -0.1700

Data Index: 5705739 (Open Web Text)

Max Activating Token Index: 100

Text #2

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.6247. Min Act: -0.1700

Data Index: 1194445 (Open Web Text)

Max Activating Token Index: 378

Text #3

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.5828. Min Act: -0.1700

Data Index: 1319354 (Open Web Text)

Max Activating Token Index: 395

Text #4

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.6250. Min Act: -0.1700

Data Index: 5260774 (Open Web Text)

Max Activating Token Index: 542

Text #5

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.5996. Min Act: -0.1700

Data Index: 483845 (Open Web Text)

Max Activating Token Index: 910

Text #6

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.5870. Min Act: -0.1700

Data Index: 4744691 (Open Web Text)

Max Activating Token Index: 283

Text #7

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.5484. Min Act: -0.1700

Data Index: 7591697 (Open Web Text)

Max Activating Token Index: 595

Text #8

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.5870. Min Act: -0.1700

Data Index: 568214 (Open Web Text)

Max Activating Token Index: 117

Text #9

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.5198. Min Act: -0.1700

Data Index: 8027370 (Open Web Text)

Max Activating Token Index: 264

Text #10

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.4786. Min Act: -0.1700

Data Index: 1335485 (Open Web Text)

Max Activating Token Index: 427

Text #11

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.5004. Min Act: -0.1700

Data Index: 1415450 (Open Web Text)

Max Activating Token Index: 922

Text #12

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.4921. Min Act: -0.1700

Data Index: 4126329 (Open Web Text)

Max Activating Token Index: 309

Text #13

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.5113. Min Act: -0.1700

Data Index: 6041558 (Open Web Text)

Max Activating Token Index: 43

Text #14

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.5091. Min Act: -0.1700

Data Index: 6700470 (Open Web Text)

Max Activating Token Index: 815

Text #15

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.4791. Min Act: -0.1700

Data Index: 3322080 (Open Web Text)

Max Activating Token Index: 41

Text #16

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.4247. Min Act: -0.1700

Data Index: 7124629 (Open Web Text)

Max Activating Token Index: 368

Text #17

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.4408. Min Act: -0.1700

Data Index: 1668005 (Open Web Text)

Max Activating Token Index: 422

Text #18

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.4918. Min Act: -0.1700

Data Index: 4457017 (Open Web Text)

Max Activating Token Index: 604

Text #19

Max Range: 4.6984. Min Range: -4.6984

Max Act: 4.3755. Min Act: -0.1700

Data Index: 6271929 (Open Web Text)

Max Activating Token Index: 1004