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

Dataset: Open Web Text

Neuron 2942 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: 4.5018. Min Range: -4.5018

Max Act: 4.5018. Min Act: -0.1700

Data Index: 714425 (Open Web Text)

Max Activating Token Index: 852

Text #1

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.1638. Min Act: -0.1700

Data Index: 8694864 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.1327. Min Act: -0.1700

Data Index: 5920325 (Open Web Text)

Max Activating Token Index: 478

Text #3

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.9932. Min Act: -0.1700

Data Index: 7692311 (Open Web Text)

Max Activating Token Index: 595

Text #4

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.9870. Min Act: -0.1700

Data Index: 2463148 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.9870. Min Act: -0.1700

Data Index: 7609418 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.0047. Min Act: -0.1700

Data Index: 7313259 (Open Web Text)

Max Activating Token Index: 827

Text #7

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.8366. Min Act: -0.1700

Data Index: 227040 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.8366. Min Act: -0.1700

Data Index: 1782263 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.8227. Min Act: -0.1700

Data Index: 3935666 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.8071. Min Act: -0.1700

Data Index: 4481757 (Open Web Text)

Max Activating Token Index: 598

Text #11

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.7659. Min Act: -0.1700

Data Index: 5079670 (Open Web Text)

Max Activating Token Index: 345

Text #12

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.8136. Min Act: -0.1700

Data Index: 4117702 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.8326. Min Act: -0.1700

Data Index: 6924259 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.8452. Min Act: -0.1700

Data Index: 4184654 (Open Web Text)

Max Activating Token Index: 320

Text #15

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.8028. Min Act: -0.1700

Data Index: 1090860 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.7547. Min Act: -0.1699

Data Index: 4184657 (Open Web Text)

Max Activating Token Index: 39

Text #17

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.7326. Min Act: -0.1700

Data Index: 4184651 (Open Web Text)

Max Activating Token Index: 433

Text #18

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.7737. Min Act: -0.1700

Data Index: 6319203 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 4.5018. Min Range: -4.5018

Max Act: 3.7811. Min Act: -0.1700

Data Index: 5680 (Open Web Text)

Max Activating Token Index: 89