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

Dataset: Open Web Text

Neuron 2015 in Layer 5

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: 3.0629. Min Range: -3.0629

Max Act: 3.0474. Min Act: -0.1700

Data Index: 5978992 (Open Web Text)

Max Activating Token Index: 865

Text #1

Max Range: 3.0629. Min Range: -3.0629

Max Act: 3.0629. Min Act: -0.1700

Data Index: 2122236 (Open Web Text)

Max Activating Token Index: 231

Text #2

Max Range: 3.0629. Min Range: -3.0629

Max Act: 3.0446. Min Act: -0.1700

Data Index: 6050944 (Open Web Text)

Max Activating Token Index: 604

Text #3

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.9621. Min Act: -0.1700

Data Index: 8798494 (Open Web Text)

Max Activating Token Index: 907

Text #4

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.9436. Min Act: -0.1700

Data Index: 1768114 (Open Web Text)

Max Activating Token Index: 47

Text #5

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.9537. Min Act: -0.1700

Data Index: 5670558 (Open Web Text)

Max Activating Token Index: 110

Text #6

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.9243. Min Act: -0.1700

Data Index: 3335283 (Open Web Text)

Max Activating Token Index: 748

Text #7

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.9188. Min Act: -0.1700

Data Index: 1643746 (Open Web Text)

Max Activating Token Index: 53

Text #8

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.9138. Min Act: -0.1700

Data Index: 8628111 (Open Web Text)

Max Activating Token Index: 151

Text #9

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.8918. Min Act: -0.1700

Data Index: 6773495 (Open Web Text)

Max Activating Token Index: 45

Text #10

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.8968. Min Act: -0.1700

Data Index: 7477946 (Open Web Text)

Max Activating Token Index: 100

Text #11

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.8951. Min Act: -0.1700

Data Index: 24486 (Open Web Text)

Max Activating Token Index: 97

Text #12

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.8776. Min Act: -0.1700

Data Index: 3496239 (Open Web Text)

Max Activating Token Index: 928

Text #13

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.8768. Min Act: -0.1700

Data Index: 5658996 (Open Web Text)

Max Activating Token Index: 746

Text #14

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.8699. Min Act: -0.1700

Data Index: 5612051 (Open Web Text)

Max Activating Token Index: 267

Text #15

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.8567. Min Act: -0.1700

Data Index: 5115655 (Open Web Text)

Max Activating Token Index: 599

Text #16

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.8617. Min Act: -0.1700

Data Index: 171348 (Open Web Text)

Max Activating Token Index: 808

Text #17

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.8732. Min Act: -0.1700

Data Index: 5940475 (Open Web Text)

Max Activating Token Index: 44

Text #18

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.8613. Min Act: -0.1700

Data Index: 425746 (Open Web Text)

Max Activating Token Index: 56

Text #19

Max Range: 3.0629. Min Range: -3.0629

Max Act: 2.8488. Min Act: -0.1700

Data Index: 25288 (Open Web Text)

Max Activating Token Index: 621