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

Dataset: Open Web Text

Neuron 2185 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: 4.3919. Min Range: -4.3919

Max Act: 4.3919. Min Act: -0.1700

Data Index: 4095719 (Open Web Text)

Max Activating Token Index: 971

Text #1

Max Range: 4.3919. Min Range: -4.3919

Max Act: 4.2545. Min Act: -0.1700

Data Index: 799687 (Open Web Text)

Max Activating Token Index: 145

Text #2

Max Range: 4.3919. Min Range: -4.3919

Max Act: 4.1592. Min Act: -0.1700

Data Index: 3865676 (Open Web Text)

Max Activating Token Index: 791

Text #3

Max Range: 4.3919. Min Range: -4.3919

Max Act: 4.1757. Min Act: -0.1700

Data Index: 6274636 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 4.3919. Min Range: -4.3919

Max Act: 4.0375. Min Act: -0.1700

Data Index: 3488376 (Open Web Text)

Max Activating Token Index: 226

Text #5

Max Range: 4.3919. Min Range: -4.3919

Max Act: 4.0349. Min Act: -0.1700

Data Index: 523000 (Open Web Text)

Max Activating Token Index: 973

Text #6

Max Range: 4.3919. Min Range: -4.3919

Max Act: 4.0474. Min Act: -0.1700

Data Index: 458082 (Open Web Text)

Max Activating Token Index: 501

Text #7

Max Range: 4.3919. Min Range: -4.3919

Max Act: 4.0163. Min Act: -0.1700

Data Index: 3108461 (Open Web Text)

Max Activating Token Index: 611

Text #8

Max Range: 4.3919. Min Range: -4.3919

Max Act: 3.9874. Min Act: -0.1700

Data Index: 4422428 (Open Web Text)

Max Activating Token Index: 725

Text #9

Max Range: 4.3919. Min Range: -4.3919

Max Act: 3.9874. Min Act: -0.1700

Data Index: 5607188 (Open Web Text)

Max Activating Token Index: 341

Text #10

Max Range: 4.3919. Min Range: -4.3919

Max Act: 3.9300. Min Act: -0.1700

Data Index: 2713727 (Open Web Text)

Max Activating Token Index: 187

Text #11

Max Range: 4.3919. Min Range: -4.3919

Max Act: 3.9875. Min Act: -0.1700

Data Index: 6887767 (Open Web Text)

Max Activating Token Index: 635

Text #12

Max Range: 4.3919. Min Range: -4.3919

Max Act: 3.8757. Min Act: -0.1700

Data Index: 639528 (Open Web Text)

Max Activating Token Index: 1002

Text #13

Max Range: 4.3919. Min Range: -4.3919

Max Act: 3.8883. Min Act: -0.1700

Data Index: 189218 (Open Web Text)

Max Activating Token Index: 311

Text #14

Max Range: 4.3919. Min Range: -4.3919

Max Act: 3.8789. Min Act: -0.1700

Data Index: 6375301 (Open Web Text)

Max Activating Token Index: 863

Text #15

Max Range: 4.3919. Min Range: -4.3919

Max Act: 3.9108. Min Act: -0.1700

Data Index: 6905640 (Open Web Text)

Max Activating Token Index: 654

Text #16

Max Range: 4.3919. Min Range: -4.3919

Max Act: 3.8998. Min Act: -0.1700

Data Index: 7973534 (Open Web Text)

Max Activating Token Index: 306

Text #17

Max Range: 4.3919. Min Range: -4.3919

Max Act: 3.9130. Min Act: -0.1700

Data Index: 7788237 (Open Web Text)

Max Activating Token Index: 809

Text #18

Max Range: 4.3919. Min Range: -4.3919

Max Act: 3.9468. Min Act: -0.1700

Data Index: 4399681 (Open Web Text)

Max Activating Token Index: 460

Text #19

Max Range: 4.3919. Min Range: -4.3919

Max Act: 3.8770. Min Act: -0.1700

Data Index: 4393123 (Open Web Text)

Max Activating Token Index: 270