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

Dataset: Open Web Text

Neuron 1964 in Layer 4

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: 2.9916. Min Range: -2.9916

Max Act: 2.9916. Min Act: -0.1700

Data Index: 5867602 (Open Web Text)

Max Activating Token Index: 389

Text #1

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.8730. Min Act: -0.1700

Data Index: 6723525 (Open Web Text)

Max Activating Token Index: 852

Text #2

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.9065. Min Act: -0.1700

Data Index: 7812173 (Open Web Text)

Max Activating Token Index: 56

Text #3

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.8910. Min Act: -0.1700

Data Index: 7899257 (Open Web Text)

Max Activating Token Index: 982

Text #4

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.9099. Min Act: -0.1700

Data Index: 8440799 (Open Web Text)

Max Activating Token Index: 971

Text #5

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.8539. Min Act: -0.1700

Data Index: 5985596 (Open Web Text)

Max Activating Token Index: 377

Text #6

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.8519. Min Act: -0.1700

Data Index: 6460235 (Open Web Text)

Max Activating Token Index: 629

Text #7

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.8666. Min Act: -0.1700

Data Index: 185121 (Open Web Text)

Max Activating Token Index: 708

Text #8

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.8577. Min Act: -0.1700

Data Index: 300912 (Open Web Text)

Max Activating Token Index: 749

Text #9

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.8462. Min Act: -0.1700

Data Index: 5280125 (Open Web Text)

Max Activating Token Index: 969

Text #10

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.8336. Min Act: -0.1700

Data Index: 5804590 (Open Web Text)

Max Activating Token Index: 967

Text #11

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.8361. Min Act: -0.1700

Data Index: 7077759 (Open Web Text)

Max Activating Token Index: 528

Text #12

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.9027. Min Act: -0.1700

Data Index: 1359657 (Open Web Text)

Max Activating Token Index: 305

Text #13

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.8044. Min Act: -0.1700

Data Index: 3133777 (Open Web Text)

Max Activating Token Index: 149

Text #14

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.7811. Min Act: -0.1700

Data Index: 5929347 (Open Web Text)

Max Activating Token Index: 263

Text #15

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.7910. Min Act: -0.1700

Data Index: 7934026 (Open Web Text)

Max Activating Token Index: 456

Text #16

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.8096. Min Act: -0.1700

Data Index: 576586 (Open Web Text)

Max Activating Token Index: 92

Text #17

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.8028. Min Act: -0.1700

Data Index: 883402 (Open Web Text)

Max Activating Token Index: 459

Text #18

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.7944. Min Act: -0.1700

Data Index: 7279594 (Open Web Text)

Max Activating Token Index: 759

Text #19

Max Range: 2.9916. Min Range: -2.9916

Max Act: 2.7645. Min Act: -0.1700

Data Index: 6614490 (Open Web Text)

Max Activating Token Index: 713