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

Dataset: Open Web Text

Neuron 1819 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: 2.0368. Min Range: -2.0368

Max Act: 2.0350. Min Act: -0.1700

Data Index: 3304444 (Open Web Text)

Max Activating Token Index: 690

Text #1

Max Range: 2.0368. Min Range: -2.0368

Max Act: 2.0330. Min Act: -0.1700

Data Index: 4839407 (Open Web Text)

Max Activating Token Index: 126

Text #2

Max Range: 2.0368. Min Range: -2.0368

Max Act: 2.0368. Min Act: -0.1700

Data Index: 5413827 (Open Web Text)

Max Activating Token Index: 803

Text #3

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9271. Min Act: -0.1700

Data Index: 5760897 (Open Web Text)

Max Activating Token Index: 438

Text #4

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8955. Min Act: -0.1700

Data Index: 7919787 (Open Web Text)

Max Activating Token Index: 251

Text #5

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8759. Min Act: -0.1700

Data Index: 2980136 (Open Web Text)

Max Activating Token Index: 868

Text #6

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9051. Min Act: -0.1700

Data Index: 5646981 (Open Web Text)

Max Activating Token Index: 1013

Text #7

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8821. Min Act: -0.1700

Data Index: 2691801 (Open Web Text)

Max Activating Token Index: 231

Text #8

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8685. Min Act: -0.1700

Data Index: 4910155 (Open Web Text)

Max Activating Token Index: 443

Text #9

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8373. Min Act: -0.1700

Data Index: 4608909 (Open Web Text)

Max Activating Token Index: 199

Text #10

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8446. Min Act: -0.1700

Data Index: 6450839 (Open Web Text)

Max Activating Token Index: 288

Text #11

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8543. Min Act: -0.1700

Data Index: 4654789 (Open Web Text)

Max Activating Token Index: 384

Text #12

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8377. Min Act: -0.1700

Data Index: 8213863 (Open Web Text)

Max Activating Token Index: 94

Text #13

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8187. Min Act: -0.1700

Data Index: 621254 (Open Web Text)

Max Activating Token Index: 477

Text #14

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.7811. Min Act: -0.1700

Data Index: 1677198 (Open Web Text)

Max Activating Token Index: 598

Text #15

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8230. Min Act: -0.1700

Data Index: 4551213 (Open Web Text)

Max Activating Token Index: 711

Text #16

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8254. Min Act: -0.1700

Data Index: 621253 (Open Web Text)

Max Activating Token Index: 808

Text #17

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8113. Min Act: -0.1700

Data Index: 2428434 (Open Web Text)

Max Activating Token Index: 82

Text #18

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8014. Min Act: -0.1700

Data Index: 4211215 (Open Web Text)

Max Activating Token Index: 686

Text #19

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8004. Min Act: -0.1700

Data Index: 8287302 (Open Web Text)

Max Activating Token Index: 910