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

Dataset: Open Web Text

Neuron 2046 in Layer 2

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: 4.0335. Min Range: -4.0335

Max Act: 4.0335. Min Act: -0.1700

Data Index: 7843595 (Open Web Text)

Max Activating Token Index: 459

Text #1

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.9067. Min Act: -0.1700

Data Index: 5029378 (Open Web Text)

Max Activating Token Index: 664

Text #2

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.8971. Min Act: -0.1700

Data Index: 5855920 (Open Web Text)

Max Activating Token Index: 238

Text #3

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.9166. Min Act: -0.1700

Data Index: 8322535 (Open Web Text)

Max Activating Token Index: 26

Text #4

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.9118. Min Act: -0.1700

Data Index: 2848609 (Open Web Text)

Max Activating Token Index: 932

Text #5

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.8878. Min Act: -0.1700

Data Index: 5029377 (Open Web Text)

Max Activating Token Index: 282

Text #6

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.8882. Min Act: -0.1700

Data Index: 8711350 (Open Web Text)

Max Activating Token Index: 151

Text #7

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.8329. Min Act: -0.1700

Data Index: 8377002 (Open Web Text)

Max Activating Token Index: 353

Text #8

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.8109. Min Act: -0.1700

Data Index: 7580364 (Open Web Text)

Max Activating Token Index: 249

Text #9

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.8147. Min Act: -0.1700

Data Index: 1934531 (Open Web Text)

Max Activating Token Index: 344

Text #10

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.8137. Min Act: -0.1700

Data Index: 528122 (Open Web Text)

Max Activating Token Index: 35

Text #11

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.8148. Min Act: -0.1700

Data Index: 4247126 (Open Web Text)

Max Activating Token Index: 473

Text #12

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.8289. Min Act: -0.1700

Data Index: 2085760 (Open Web Text)

Max Activating Token Index: 231

Text #13

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.7341. Min Act: -0.1700

Data Index: 2843202 (Open Web Text)

Max Activating Token Index: 404

Text #14

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.7141. Min Act: -0.1700

Data Index: 8154618 (Open Web Text)

Max Activating Token Index: 412

Text #15

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.7337. Min Act: -0.1700

Data Index: 7512234 (Open Web Text)

Max Activating Token Index: 778

Text #16

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.7243. Min Act: -0.1700

Data Index: 1727278 (Open Web Text)

Max Activating Token Index: 688

Text #17

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.7074. Min Act: -0.1700

Data Index: 3154576 (Open Web Text)

Max Activating Token Index: 22

Text #18

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.7475. Min Act: -0.1700

Data Index: 4486764 (Open Web Text)

Max Activating Token Index: 267

Text #19

Max Range: 4.0335. Min Range: -4.0335

Max Act: 3.7068. Min Act: -0.1700

Data Index: 1308648 (Open Web Text)

Max Activating Token Index: 224