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

Dataset: Open Web Text

Neuron 976 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: 4.9093. Min Range: -4.9093

Max Act: 4.9093. Min Act: -0.1700

Data Index: 3040740 (Open Web Text)

Max Activating Token Index: 592

Text #1

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.8853. Min Act: -0.1700

Data Index: 5893977 (Open Web Text)

Max Activating Token Index: 503

Text #2

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.8291. Min Act: -0.1700

Data Index: 3497081 (Open Web Text)

Max Activating Token Index: 942

Text #3

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.8772. Min Act: -0.1700

Data Index: 7362371 (Open Web Text)

Max Activating Token Index: 723

Text #4

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.8408. Min Act: -0.1700

Data Index: 4231717 (Open Web Text)

Max Activating Token Index: 609

Text #5

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.8450. Min Act: -0.1700

Data Index: 5893979 (Open Web Text)

Max Activating Token Index: 230

Text #6

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.8600. Min Act: -0.1700

Data Index: 8045288 (Open Web Text)

Max Activating Token Index: 400

Text #7

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.8346. Min Act: -0.1700

Data Index: 3541802 (Open Web Text)

Max Activating Token Index: 664

Text #8

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.7974. Min Act: -0.1700

Data Index: 1668200 (Open Web Text)

Max Activating Token Index: 324

Text #9

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.7891. Min Act: -0.1700

Data Index: 6376254 (Open Web Text)

Max Activating Token Index: 892

Text #10

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.7800. Min Act: -0.1700

Data Index: 8454189 (Open Web Text)

Max Activating Token Index: 533

Text #11

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.7435. Min Act: -0.1700

Data Index: 2489950 (Open Web Text)

Max Activating Token Index: 737

Text #12

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.7578. Min Act: -0.1700

Data Index: 3560152 (Open Web Text)

Max Activating Token Index: 364

Text #13

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.7429. Min Act: -0.1700

Data Index: 539836 (Open Web Text)

Max Activating Token Index: 274

Text #14

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.7582. Min Act: -0.1700

Data Index: 434782 (Open Web Text)

Max Activating Token Index: 361

Text #15

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.7472. Min Act: -0.1700

Data Index: 4750132 (Open Web Text)

Max Activating Token Index: 560

Text #16

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.7550. Min Act: -0.1700

Data Index: 4696909 (Open Web Text)

Max Activating Token Index: 140

Text #17

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.7591. Min Act: -0.1700

Data Index: 7002141 (Open Web Text)

Max Activating Token Index: 350

Text #18

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.7227. Min Act: -0.1700

Data Index: 3417790 (Open Web Text)

Max Activating Token Index: 128

Text #19

Max Range: 4.9093. Min Range: -4.9093

Max Act: 4.7331. Min Act: -0.1700

Data Index: 2500732 (Open Web Text)

Max Activating Token Index: 967