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

Dataset: Open Web Text

Neuron 245 in Layer 6

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: 4.5317. Min Range: -4.5317

Max Act: 4.5317. Min Act: -0.1700

Data Index: 3940686 (Open Web Text)

Max Activating Token Index: 691

Text #1

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.3242. Min Act: -0.1700

Data Index: 1918888 (Open Web Text)

Max Activating Token Index: 931

Text #2

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.3268. Min Act: -0.1700

Data Index: 8498721 (Open Web Text)

Max Activating Token Index: 664

Text #3

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.3100. Min Act: -0.1700

Data Index: 2626405 (Open Web Text)

Max Activating Token Index: 804

Text #4

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.2915. Min Act: -0.1700

Data Index: 655074 (Open Web Text)

Max Activating Token Index: 894

Text #5

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.2455. Min Act: -0.1700

Data Index: 3027535 (Open Web Text)

Max Activating Token Index: 919

Text #6

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.2626. Min Act: -0.1700

Data Index: 5752664 (Open Web Text)

Max Activating Token Index: 294

Text #7

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.2220. Min Act: -0.1700

Data Index: 3821105 (Open Web Text)

Max Activating Token Index: 490

Text #8

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.2533. Min Act: -0.1700

Data Index: 6865704 (Open Web Text)

Max Activating Token Index: 925

Text #9

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.2050. Min Act: -0.1700

Data Index: 4510489 (Open Web Text)

Max Activating Token Index: 464

Text #10

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.1967. Min Act: -0.1700

Data Index: 4507798 (Open Web Text)

Max Activating Token Index: 923

Text #11

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.1893. Min Act: -0.1700

Data Index: 6288114 (Open Web Text)

Max Activating Token Index: 380

Text #12

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.1540. Min Act: -0.1700

Data Index: 1999440 (Open Web Text)

Max Activating Token Index: 1020

Text #13

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.1532. Min Act: -0.1700

Data Index: 4531829 (Open Web Text)

Max Activating Token Index: 522

Text #14

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.1684. Min Act: -0.1700

Data Index: 7920099 (Open Web Text)

Max Activating Token Index: 891

Text #15

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.1017. Min Act: -0.1700

Data Index: 2619558 (Open Web Text)

Max Activating Token Index: 404

Text #16

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.1064. Min Act: -0.1700

Data Index: 485554 (Open Web Text)

Max Activating Token Index: 267

Text #17

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.0456. Min Act: -0.1700

Data Index: 1400441 (Open Web Text)

Max Activating Token Index: 884

Text #18

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.0427. Min Act: -0.1700

Data Index: 5942097 (Open Web Text)

Max Activating Token Index: 602

Text #19

Max Range: 4.5317. Min Range: -4.5317

Max Act: 4.0229. Min Act: -0.1700

Data Index: 5890639 (Open Web Text)

Max Activating Token Index: 427