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

Dataset: Open Web Text

Neuron 180 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: 4.1198. Min Range: -4.1198

Max Act: 4.1047. Min Act: -0.1700

Data Index: 1282478 (Open Web Text)

Max Activating Token Index: 442

Text #1

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.1048. Min Act: -0.1700

Data Index: 4659211 (Open Web Text)

Max Activating Token Index: 544

Text #2

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.1134. Min Act: -0.1700

Data Index: 4238632 (Open Web Text)

Max Activating Token Index: 280

Text #3

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.1169. Min Act: -0.1700

Data Index: 3847205 (Open Web Text)

Max Activating Token Index: 346

Text #4

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.1053. Min Act: -0.1700

Data Index: 8388889 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.1175. Min Act: -0.1700

Data Index: 4827132 (Open Web Text)

Max Activating Token Index: 306

Text #6

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.0845. Min Act: -0.1700

Data Index: 1644828 (Open Web Text)

Max Activating Token Index: 85

Text #7

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.0624. Min Act: -0.1700

Data Index: 8724556 (Open Web Text)

Max Activating Token Index: 48

Text #8

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.0607. Min Act: -0.1700

Data Index: 3629942 (Open Web Text)

Max Activating Token Index: 1015

Text #9

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.0971. Min Act: -0.1700

Data Index: 930912 (Open Web Text)

Max Activating Token Index: 807

Text #10

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.0838. Min Act: -0.1700

Data Index: 7989857 (Open Web Text)

Max Activating Token Index: 523

Text #11

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.1198. Min Act: -0.1700

Data Index: 7679742 (Open Web Text)

Max Activating Token Index: 473

Text #12

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.0704. Min Act: -0.1700

Data Index: 7015604 (Open Web Text)

Max Activating Token Index: 408

Text #13

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.0945. Min Act: -0.1700

Data Index: 6456678 (Open Web Text)

Max Activating Token Index: 50

Text #14

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.0681. Min Act: -0.1700

Data Index: 2873895 (Open Web Text)

Max Activating Token Index: 94

Text #15

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.0837. Min Act: -0.1700

Data Index: 6291825 (Open Web Text)

Max Activating Token Index: 493

Text #16

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.0892. Min Act: -0.1700

Data Index: 6140754 (Open Web Text)

Max Activating Token Index: 399

Text #17

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.0992. Min Act: -0.1700

Data Index: 1136301 (Open Web Text)

Max Activating Token Index: 506

Text #18

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.0874. Min Act: -0.1700

Data Index: 5083662 (Open Web Text)

Max Activating Token Index: 403

Text #19

Max Range: 4.1198. Min Range: -4.1198

Max Act: 4.0348. Min Act: -0.1700

Data Index: 1225130 (Open Web Text)

Max Activating Token Index: 160