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

Dataset: Open Web Text

Neuron 2718 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: 0.7422. Min Range: -0.7422

Max Act: 0.7422. Min Act: -0.1700

Data Index: 8433713 (Open Web Text)

Max Activating Token Index: 760

Text #1

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7402. Min Act: -0.1700

Data Index: 7452922 (Open Web Text)

Max Activating Token Index: 766

Text #2

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7318. Min Act: -0.1700

Data Index: 4509349 (Open Web Text)

Max Activating Token Index: 771

Text #3

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7230. Min Act: -0.1700

Data Index: 6966254 (Open Web Text)

Max Activating Token Index: 758

Text #4

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7174. Min Act: -0.1700

Data Index: 3322939 (Open Web Text)

Max Activating Token Index: 763

Text #5

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7193. Min Act: -0.1700

Data Index: 5201681 (Open Web Text)

Max Activating Token Index: 753

Text #6

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7129. Min Act: -0.1700

Data Index: 3734422 (Open Web Text)

Max Activating Token Index: 758

Text #7

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7162. Min Act: -0.1700

Data Index: 5682152 (Open Web Text)

Max Activating Token Index: 769

Text #8

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7112. Min Act: -0.1700

Data Index: 4351162 (Open Web Text)

Max Activating Token Index: 772

Text #9

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7120. Min Act: -0.1700

Data Index: 3164080 (Open Web Text)

Max Activating Token Index: 773

Text #10

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7152. Min Act: -0.1700

Data Index: 4645949 (Open Web Text)

Max Activating Token Index: 775

Text #11

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7003. Min Act: -0.1700

Data Index: 5392432 (Open Web Text)

Max Activating Token Index: 773

Text #12

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6983. Min Act: -0.1699

Data Index: 1899986 (Open Web Text)

Max Activating Token Index: 755

Text #13

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7033. Min Act: -0.1700

Data Index: 5637626 (Open Web Text)

Max Activating Token Index: 752

Text #14

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6947. Min Act: -0.1700

Data Index: 3837297 (Open Web Text)

Max Activating Token Index: 750

Text #15

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.7062. Min Act: -0.1700

Data Index: 716636 (Open Web Text)

Max Activating Token Index: 761

Text #16

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6966. Min Act: -0.1700

Data Index: 365818 (Open Web Text)

Max Activating Token Index: 765

Text #17

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6960. Min Act: -0.1700

Data Index: 1008348 (Open Web Text)

Max Activating Token Index: 761

Text #18

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6957. Min Act: -0.1700

Data Index: 2194877 (Open Web Text)

Max Activating Token Index: 756

Text #19

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.6888. Min Act: -0.1700

Data Index: 6555450 (Open Web Text)

Max Activating Token Index: 757