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

Dataset: Open Web Text

Neuron 2686 in Layer 3

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: 1.8917. Min Range: -1.8917

Max Act: 1.8917. Min Act: -0.1700

Data Index: 1242058 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.8129. Min Act: -0.1700

Data Index: 3648976 (Open Web Text)

Max Activating Token Index: 146

Text #2

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7622. Min Act: -0.1700

Data Index: 5592906 (Open Web Text)

Max Activating Token Index: 345

Text #3

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7741. Min Act: -0.1700

Data Index: 5580504 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7492. Min Act: -0.1700

Data Index: 8042897 (Open Web Text)

Max Activating Token Index: 465

Text #5

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6975. Min Act: -0.1700

Data Index: 1940484 (Open Web Text)

Max Activating Token Index: 837

Text #6

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6992. Min Act: -0.1700

Data Index: 6615433 (Open Web Text)

Max Activating Token Index: 346

Text #7

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7080. Min Act: -0.1700

Data Index: 8819040 (Open Web Text)

Max Activating Token Index: 210

Text #8

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7140. Min Act: -0.1700

Data Index: 5783440 (Open Web Text)

Max Activating Token Index: 606

Text #9

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7017. Min Act: -0.1700

Data Index: 7485145 (Open Web Text)

Max Activating Token Index: 804

Text #10

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6950. Min Act: -0.1700

Data Index: 5519818 (Open Web Text)

Max Activating Token Index: 398

Text #11

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6927. Min Act: -0.1700

Data Index: 1242057 (Open Web Text)

Max Activating Token Index: 794

Text #12

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6994. Min Act: -0.1700

Data Index: 2698654 (Open Web Text)

Max Activating Token Index: 592

Text #13

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6933. Min Act: -0.1700

Data Index: 2953484 (Open Web Text)

Max Activating Token Index: 130

Text #14

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6550. Min Act: -0.1700

Data Index: 6484631 (Open Web Text)

Max Activating Token Index: 345

Text #15

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6743. Min Act: -0.1700

Data Index: 8298112 (Open Web Text)

Max Activating Token Index: 199

Text #16

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6562. Min Act: -0.1700

Data Index: 5099352 (Open Web Text)

Max Activating Token Index: 928

Text #17

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6649. Min Act: -0.1700

Data Index: 7697364 (Open Web Text)

Max Activating Token Index: 709

Text #18

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6453. Min Act: -0.1700

Data Index: 7853300 (Open Web Text)

Max Activating Token Index: 364

Text #19

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6661. Min Act: -0.1700

Data Index: 7349316 (Open Web Text)

Max Activating Token Index: 178