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

Dataset: Open Web Text

Neuron 2395 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: 5.0138. Min Range: -5.0138

Max Act: 5.0138. Min Act: -0.1700

Data Index: 5030901 (Open Web Text)

Max Activating Token Index: 283

Text #1

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.8906. Min Act: -0.1700

Data Index: 5922424 (Open Web Text)

Max Activating Token Index: 291

Text #2

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.9079. Min Act: -0.1700

Data Index: 750331 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.9075. Min Act: -0.1700

Data Index: 4870244 (Open Web Text)

Max Activating Token Index: 1020

Text #4

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.8813. Min Act: -0.1700

Data Index: 1181739 (Open Web Text)

Max Activating Token Index: 415

Text #5

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.8736. Min Act: -0.1700

Data Index: 7034202 (Open Web Text)

Max Activating Token Index: 528

Text #6

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.8423. Min Act: -0.1700

Data Index: 2846790 (Open Web Text)

Max Activating Token Index: 720

Text #7

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.8363. Min Act: -0.1700

Data Index: 3922778 (Open Web Text)

Max Activating Token Index: 200

Text #8

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7944. Min Act: -0.1700

Data Index: 5875191 (Open Web Text)

Max Activating Token Index: 977

Text #9

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7576. Min Act: -0.1700

Data Index: 20412 (Open Web Text)

Max Activating Token Index: 906

Text #10

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.8042. Min Act: -0.1700

Data Index: 5754885 (Open Web Text)

Max Activating Token Index: 528

Text #11

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7506. Min Act: -0.1700

Data Index: 2635996 (Open Web Text)

Max Activating Token Index: 496

Text #12

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7087. Min Act: -0.1700

Data Index: 2567 (Open Web Text)

Max Activating Token Index: 519

Text #13

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7104. Min Act: -0.1700

Data Index: 7913522 (Open Web Text)

Max Activating Token Index: 755

Text #14

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7497. Min Act: -0.1700

Data Index: 3142523 (Open Web Text)

Max Activating Token Index: 19

Text #15

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7830. Min Act: -0.1700

Data Index: 750330 (Open Web Text)

Max Activating Token Index: 158

Text #16

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.6379. Min Act: -0.1700

Data Index: 1914229 (Open Web Text)

Max Activating Token Index: 593

Text #17

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7485. Min Act: -0.1700

Data Index: 4088409 (Open Web Text)

Max Activating Token Index: 455

Text #18

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.6864. Min Act: -0.1700

Data Index: 2027357 (Open Web Text)

Max Activating Token Index: 25

Text #19

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7239. Min Act: -0.1700

Data Index: 7913512 (Open Web Text)

Max Activating Token Index: 732