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

Dataset: Open Web Text

Neuron 3009 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: 3.6227. Min Range: -3.6227

Max Act: 3.6227. Min Act: -0.1700

Data Index: 1340465 (Open Web Text)

Max Activating Token Index: 50

Text #1

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.5235. Min Act: -0.1700

Data Index: 889228 (Open Web Text)

Max Activating Token Index: 747

Text #2

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.5026. Min Act: -0.1700

Data Index: 7641155 (Open Web Text)

Max Activating Token Index: 113

Text #3

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4884. Min Act: -0.1700

Data Index: 8598828 (Open Web Text)

Max Activating Token Index: 977

Text #4

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4498. Min Act: -0.1700

Data Index: 7735644 (Open Web Text)

Max Activating Token Index: 769

Text #5

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4493. Min Act: -0.1700

Data Index: 6565431 (Open Web Text)

Max Activating Token Index: 63

Text #6

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4220. Min Act: -0.1700

Data Index: 6834490 (Open Web Text)

Max Activating Token Index: 490

Text #7

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4259. Min Act: -0.1700

Data Index: 8448101 (Open Web Text)

Max Activating Token Index: 997

Text #8

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4201. Min Act: -0.1700

Data Index: 4732768 (Open Web Text)

Max Activating Token Index: 819

Text #9

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4081. Min Act: -0.1700

Data Index: 1749672 (Open Web Text)

Max Activating Token Index: 869

Text #10

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4066. Min Act: -0.1700

Data Index: 4907499 (Open Web Text)

Max Activating Token Index: 974

Text #11

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.3962. Min Act: -0.1700

Data Index: 3113357 (Open Web Text)

Max Activating Token Index: 263

Text #12

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.3949. Min Act: -0.1700

Data Index: 1655706 (Open Web Text)

Max Activating Token Index: 272

Text #13

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.3596. Min Act: -0.1700

Data Index: 561499 (Open Web Text)

Max Activating Token Index: 443

Text #14

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.3768. Min Act: -0.1700

Data Index: 3260794 (Open Web Text)

Max Activating Token Index: 116

Text #15

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.3832. Min Act: -0.1700

Data Index: 4147961 (Open Web Text)

Max Activating Token Index: 631

Text #16

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.3706. Min Act: -0.1700

Data Index: 299530 (Open Web Text)

Max Activating Token Index: 121

Text #17

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.3613. Min Act: -0.1700

Data Index: 1573364 (Open Web Text)

Max Activating Token Index: 963

Text #18

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.3761. Min Act: -0.1700

Data Index: 190591 (Open Web Text)

Max Activating Token Index: 506

Text #19

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.3515. Min Act: -0.1700

Data Index: 1469664 (Open Web Text)

Max Activating Token Index: 869