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

Dataset: Open Web Text

Neuron 1243 in Layer 4

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: 3.2603. Min Range: -3.2603

Max Act: 3.2603. Min Act: -0.1700

Data Index: 4055029 (Open Web Text)

Max Activating Token Index: 788

Text #1

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.2150. Min Act: -0.1700

Data Index: 5085939 (Open Web Text)

Max Activating Token Index: 757

Text #2

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1929. Min Act: -0.1700

Data Index: 7004255 (Open Web Text)

Max Activating Token Index: 608

Text #3

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1173. Min Act: -0.1700

Data Index: 7575062 (Open Web Text)

Max Activating Token Index: 960

Text #4

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0443. Min Act: -0.1700

Data Index: 5366205 (Open Web Text)

Max Activating Token Index: 872

Text #5

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0693. Min Act: -0.1700

Data Index: 4587402 (Open Web Text)

Max Activating Token Index: 858

Text #6

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0516. Min Act: -0.1700

Data Index: 3534177 (Open Web Text)

Max Activating Token Index: 728

Text #7

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0578. Min Act: -0.1700

Data Index: 1292179 (Open Web Text)

Max Activating Token Index: 692

Text #8

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0636. Min Act: -0.1700

Data Index: 2830805 (Open Web Text)

Max Activating Token Index: 663

Text #9

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0180. Min Act: -0.1700

Data Index: 153277 (Open Web Text)

Max Activating Token Index: 1006

Text #10

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0303. Min Act: -0.1700

Data Index: 754384 (Open Web Text)

Max Activating Token Index: 679

Text #11

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0219. Min Act: -0.1700

Data Index: 4406140 (Open Web Text)

Max Activating Token Index: 712

Text #12

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0393. Min Act: -0.1700

Data Index: 5785277 (Open Web Text)

Max Activating Token Index: 894

Text #13

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0522. Min Act: -0.1700

Data Index: 1698283 (Open Web Text)

Max Activating Token Index: 701

Text #14

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0242. Min Act: -0.1700

Data Index: 1826598 (Open Web Text)

Max Activating Token Index: 559

Text #15

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0330. Min Act: -0.1700

Data Index: 2956173 (Open Web Text)

Max Activating Token Index: 704

Text #16

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.9935. Min Act: -0.1700

Data Index: 2889032 (Open Web Text)

Max Activating Token Index: 951

Text #17

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0188. Min Act: -0.1700

Data Index: 813489 (Open Web Text)

Max Activating Token Index: 946

Text #18

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0138. Min Act: -0.1700

Data Index: 1367367 (Open Web Text)

Max Activating Token Index: 934

Text #19

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0160. Min Act: -0.1700

Data Index: 546486 (Open Web Text)

Max Activating Token Index: 994