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

Dataset: Open Web Text

Neuron 2930 in Layer 1

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: 1.9854. Min Range: -1.9854

Max Act: 1.9854. Min Act: -0.1700

Data Index: 7087144 (Open Web Text)

Max Activating Token Index: 399

Text #1

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.9775. Min Act: -0.1700

Data Index: 4717913 (Open Web Text)

Max Activating Token Index: 566

Text #2

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.9708. Min Act: -0.1700

Data Index: 1469468 (Open Web Text)

Max Activating Token Index: 542

Text #3

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.9508. Min Act: -0.1700

Data Index: 181992 (Open Web Text)

Max Activating Token Index: 938

Text #4

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.9519. Min Act: -0.1699

Data Index: 3516855 (Open Web Text)

Max Activating Token Index: 153

Text #5

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.9106. Min Act: -0.1700

Data Index: 3012004 (Open Web Text)

Max Activating Token Index: 104

Text #6

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.9154. Min Act: -0.1700

Data Index: 2876977 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.9083. Min Act: -0.1700

Data Index: 463873 (Open Web Text)

Max Activating Token Index: 581

Text #8

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.8961. Min Act: -0.1700

Data Index: 1301806 (Open Web Text)

Max Activating Token Index: 631

Text #9

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.8991. Min Act: -0.1700

Data Index: 4627466 (Open Web Text)

Max Activating Token Index: 124

Text #10

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.8945. Min Act: -0.1700

Data Index: 193881 (Open Web Text)

Max Activating Token Index: 506

Text #11

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.9002. Min Act: -0.1700

Data Index: 3287725 (Open Web Text)

Max Activating Token Index: 256

Text #12

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.9010. Min Act: -0.1700

Data Index: 7506410 (Open Web Text)

Max Activating Token Index: 367

Text #13

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.8893. Min Act: -0.1700

Data Index: 5424076 (Open Web Text)

Max Activating Token Index: 50

Text #14

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.8901. Min Act: -0.1700

Data Index: 765254 (Open Web Text)

Max Activating Token Index: 669

Text #15

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.8954. Min Act: -0.1700

Data Index: 1864792 (Open Web Text)

Max Activating Token Index: 357

Text #16

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.8791. Min Act: -0.1700

Data Index: 3622241 (Open Web Text)

Max Activating Token Index: 97

Text #17

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.8917. Min Act: -0.1700

Data Index: 893117 (Open Web Text)

Max Activating Token Index: 58

Text #18

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.8683. Min Act: -0.1700

Data Index: 6142547 (Open Web Text)

Max Activating Token Index: 673

Text #19

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.8724. Min Act: -0.1700

Data Index: 4056009 (Open Web Text)

Max Activating Token Index: 301