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

Dataset: Open Web Text

Neuron 2865 in Layer 6

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: 4.9782. Min Range: -4.9782

Max Act: 4.9782. Min Act: -0.1700

Data Index: 6200176 (Open Web Text)

Max Activating Token Index: 138

Text #1

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.8962. Min Act: -0.1700

Data Index: 525776 (Open Web Text)

Max Activating Token Index: 697

Text #2

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.7367. Min Act: -0.1700

Data Index: 2500144 (Open Web Text)

Max Activating Token Index: 389

Text #3

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.7315. Min Act: -0.1700

Data Index: 7641542 (Open Web Text)

Max Activating Token Index: 841

Text #4

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.7121. Min Act: -0.1700

Data Index: 2509898 (Open Web Text)

Max Activating Token Index: 582

Text #5

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.7035. Min Act: -0.1700

Data Index: 7294871 (Open Web Text)

Max Activating Token Index: 659

Text #6

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.6441. Min Act: -0.1700

Data Index: 5718921 (Open Web Text)

Max Activating Token Index: 60

Text #7

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.6785. Min Act: -0.1700

Data Index: 1304641 (Open Web Text)

Max Activating Token Index: 975

Text #8

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.6333. Min Act: -0.1700

Data Index: 4701266 (Open Web Text)

Max Activating Token Index: 132

Text #9

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.6512. Min Act: -0.1700

Data Index: 5596684 (Open Web Text)

Max Activating Token Index: 306

Text #10

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.6305. Min Act: -0.1700

Data Index: 6871141 (Open Web Text)

Max Activating Token Index: 548

Text #11

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.6582. Min Act: -0.1700

Data Index: 7227855 (Open Web Text)

Max Activating Token Index: 493

Text #12

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.6112. Min Act: -0.1700

Data Index: 3662164 (Open Web Text)

Max Activating Token Index: 407

Text #13

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.6262. Min Act: -0.1700

Data Index: 5658803 (Open Web Text)

Max Activating Token Index: 108

Text #14

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.5775. Min Act: -0.1700

Data Index: 5278743 (Open Web Text)

Max Activating Token Index: 769

Text #15

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.6295. Min Act: -0.1700

Data Index: 1733585 (Open Web Text)

Max Activating Token Index: 517

Text #16

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.5972. Min Act: -0.1700

Data Index: 4744320 (Open Web Text)

Max Activating Token Index: 589

Text #17

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.6040. Min Act: -0.1700

Data Index: 1684948 (Open Web Text)

Max Activating Token Index: 98

Text #18

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.5772. Min Act: -0.1700

Data Index: 2659937 (Open Web Text)

Max Activating Token Index: 298

Text #19

Max Range: 4.9782. Min Range: -4.9782

Max Act: 4.5938. Min Act: -0.1700

Data Index: 3606071 (Open Web Text)

Max Activating Token Index: 391