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

Dataset: Open Web Text

Neuron 2833 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: 2.8016. Min Range: -2.8016

Max Act: 2.7843. Min Act: -0.1700

Data Index: 4232170 (Open Web Text)

Max Activating Token Index: 744

Text #1

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.8016. Min Act: -0.1700

Data Index: 5370670 (Open Web Text)

Max Activating Token Index: 452

Text #2

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7834. Min Act: -0.1700

Data Index: 4967401 (Open Web Text)

Max Activating Token Index: 293

Text #3

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7744. Min Act: -0.1700

Data Index: 6822905 (Open Web Text)

Max Activating Token Index: 532

Text #4

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7642. Min Act: -0.1700

Data Index: 2292332 (Open Web Text)

Max Activating Token Index: 492

Text #5

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7571. Min Act: -0.1700

Data Index: 6822912 (Open Web Text)

Max Activating Token Index: 538

Text #6

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7438. Min Act: -0.1700

Data Index: 5128640 (Open Web Text)

Max Activating Token Index: 466

Text #7

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7622. Min Act: -0.1700

Data Index: 6742166 (Open Web Text)

Max Activating Token Index: 677

Text #8

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7300. Min Act: -0.1700

Data Index: 3079257 (Open Web Text)

Max Activating Token Index: 724

Text #9

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7426. Min Act: -0.1700

Data Index: 6319334 (Open Web Text)

Max Activating Token Index: 662

Text #10

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7398. Min Act: -0.1700

Data Index: 2089666 (Open Web Text)

Max Activating Token Index: 624

Text #11

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7343. Min Act: -0.1700

Data Index: 5370665 (Open Web Text)

Max Activating Token Index: 758

Text #12

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7133. Min Act: -0.1700

Data Index: 5046379 (Open Web Text)

Max Activating Token Index: 788

Text #13

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7165. Min Act: -0.1700

Data Index: 4126488 (Open Web Text)

Max Activating Token Index: 694

Text #14

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7279. Min Act: -0.1700

Data Index: 6920254 (Open Web Text)

Max Activating Token Index: 764

Text #15

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7377. Min Act: -0.1700

Data Index: 6822911 (Open Web Text)

Max Activating Token Index: 669

Text #16

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.6989. Min Act: -0.1700

Data Index: 5626098 (Open Web Text)

Max Activating Token Index: 473

Text #17

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7014. Min Act: -0.1700

Data Index: 4967404 (Open Web Text)

Max Activating Token Index: 1016

Text #18

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7052. Min Act: -0.1700

Data Index: 574222 (Open Web Text)

Max Activating Token Index: 834

Text #19

Max Range: 2.8016. Min Range: -2.8016

Max Act: 2.7046. Min Act: -0.1700

Data Index: 6647442 (Open Web Text)

Max Activating Token Index: 417