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

Dataset: Open Web Text

Neuron 290 in Layer 6

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: 4604128 (Open Web Text)

Max Activating Token Index: 317

Text #1

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.4887. Min Act: -0.1700

Data Index: 291745 (Open Web Text)

Max Activating Token Index: 256

Text #2

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.4048. Min Act: -0.1700

Data Index: 8773297 (Open Web Text)

Max Activating Token Index: 688

Text #3

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3505. Min Act: -0.1700

Data Index: 4468620 (Open Web Text)

Max Activating Token Index: 464

Text #4

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3701. Min Act: -0.1700

Data Index: 1698622 (Open Web Text)

Max Activating Token Index: 441

Text #5

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3734. Min Act: -0.1700

Data Index: 5327681 (Open Web Text)

Max Activating Token Index: 98

Text #6

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3343. Min Act: -0.1700

Data Index: 2579495 (Open Web Text)

Max Activating Token Index: 745

Text #7

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3117. Min Act: -0.1700

Data Index: 1839332 (Open Web Text)

Max Activating Token Index: 736

Text #8

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3314. Min Act: -0.1700

Data Index: 5959205 (Open Web Text)

Max Activating Token Index: 966

Text #9

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3207. Min Act: -0.1700

Data Index: 8261019 (Open Web Text)

Max Activating Token Index: 986

Text #10

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3212. Min Act: -0.1700

Data Index: 6034965 (Open Web Text)

Max Activating Token Index: 826

Text #11

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3449. Min Act: -0.1700

Data Index: 6981760 (Open Web Text)

Max Activating Token Index: 708

Text #12

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3393. Min Act: -0.1700

Data Index: 1084031 (Open Web Text)

Max Activating Token Index: 912

Text #13

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3199. Min Act: -0.1700

Data Index: 3222545 (Open Web Text)

Max Activating Token Index: 873

Text #14

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3256. Min Act: -0.1700

Data Index: 5335887 (Open Web Text)

Max Activating Token Index: 595

Text #15

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3216. Min Act: -0.1700

Data Index: 838055 (Open Web Text)

Max Activating Token Index: 80

Text #16

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.2989. Min Act: -0.1700

Data Index: 369762 (Open Web Text)

Max Activating Token Index: 1013

Text #17

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3049. Min Act: -0.1700

Data Index: 4283922 (Open Web Text)

Max Activating Token Index: 756

Text #18

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3102. Min Act: -0.1700

Data Index: 1264875 (Open Web Text)

Max Activating Token Index: 377

Text #19

Max Range: 4.5018. Min Range: -4.5018

Max Act: 4.3168. Min Act: -0.1700

Data Index: 6797131 (Open Web Text)

Max Activating Token Index: 23