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

Dataset: Open Web Text

Neuron 1485 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: 3.2127. Min Range: -3.2127

Max Act: 3.2127. Min Act: -0.1700

Data Index: 2551975 (Open Web Text)

Max Activating Token Index: 597

Text #1

Max Range: 3.2127. Min Range: -3.2127

Max Act: 3.0903. Min Act: -0.1700

Data Index: 3967776 (Open Web Text)

Max Activating Token Index: 404

Text #2

Max Range: 3.2127. Min Range: -3.2127

Max Act: 3.0288. Min Act: -0.1700

Data Index: 5940604 (Open Web Text)

Max Activating Token Index: 623

Text #3

Max Range: 3.2127. Min Range: -3.2127

Max Act: 3.0603. Min Act: -0.1700

Data Index: 155934 (Open Web Text)

Max Activating Token Index: 635

Text #4

Max Range: 3.2127. Min Range: -3.2127

Max Act: 3.0145. Min Act: -0.1700

Data Index: 6638225 (Open Web Text)

Max Activating Token Index: 999

Text #5

Max Range: 3.2127. Min Range: -3.2127

Max Act: 3.0060. Min Act: -0.1700

Data Index: 5390806 (Open Web Text)

Max Activating Token Index: 825

Text #6

Max Range: 3.2127. Min Range: -3.2127

Max Act: 2.9805. Min Act: -0.1700

Data Index: 7520358 (Open Web Text)

Max Activating Token Index: 708

Text #7

Max Range: 3.2127. Min Range: -3.2127

Max Act: 2.9881. Min Act: -0.1700

Data Index: 3270100 (Open Web Text)

Max Activating Token Index: 911

Text #8

Max Range: 3.2127. Min Range: -3.2127

Max Act: 2.9864. Min Act: -0.1700

Data Index: 5741036 (Open Web Text)

Max Activating Token Index: 966

Text #9

Max Range: 3.2127. Min Range: -3.2127

Max Act: 2.9762. Min Act: -0.1700

Data Index: 7970723 (Open Web Text)

Max Activating Token Index: 367

Text #10

Max Range: 3.2127. Min Range: -3.2127

Max Act: 2.9761. Min Act: -0.1700

Data Index: 8747796 (Open Web Text)

Max Activating Token Index: 167

Text #11

Max Range: 3.2127. Min Range: -3.2127

Max Act: 2.9724. Min Act: -0.1700

Data Index: 8407966 (Open Web Text)

Max Activating Token Index: 522

Text #12

Max Range: 3.2127. Min Range: -3.2127

Max Act: 2.9808. Min Act: -0.1700

Data Index: 2499622 (Open Web Text)

Max Activating Token Index: 668

Text #13

Max Range: 3.2127. Min Range: -3.2127

Max Act: 2.9749. Min Act: -0.1700

Data Index: 8814287 (Open Web Text)

Max Activating Token Index: 836

Text #14

Max Range: 3.2127. Min Range: -3.2127

Max Act: 2.9616. Min Act: -0.1700

Data Index: 5949620 (Open Web Text)

Max Activating Token Index: 628

Text #15

Max Range: 3.2127. Min Range: -3.2127

Max Act: 2.9344. Min Act: -0.1700

Data Index: 494616 (Open Web Text)

Max Activating Token Index: 287

Text #16

Max Range: 3.2127. Min Range: -3.2127

Max Act: 2.9495. Min Act: -0.1700

Data Index: 3085331 (Open Web Text)

Max Activating Token Index: 160

Text #17

Max Range: 3.2127. Min Range: -3.2127

Max Act: 2.9454. Min Act: -0.1700

Data Index: 2177650 (Open Web Text)

Max Activating Token Index: 478

Text #18

Max Range: 3.2127. Min Range: -3.2127

Max Act: 2.9587. Min Act: -0.1700

Data Index: 1772456 (Open Web Text)

Max Activating Token Index: 284

Text #19

Max Range: 3.2127. Min Range: -3.2127

Max Act: 2.9584. Min Act: -0.1700

Data Index: 5075451 (Open Web Text)

Max Activating Token Index: 1011