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

Dataset: Open Web Text

Neuron 2499 in Layer 5

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: 4.6542. Min Range: -4.6542

Max Act: 4.6542. Min Act: -0.1700

Data Index: 1328707 (Open Web Text)

Max Activating Token Index: 480

Text #1

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.6264. Min Act: -0.1700

Data Index: 2619824 (Open Web Text)

Max Activating Token Index: 750

Text #2

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.6080. Min Act: -0.1700

Data Index: 7471752 (Open Web Text)

Max Activating Token Index: 52

Text #3

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.6024. Min Act: -0.1700

Data Index: 3894996 (Open Web Text)

Max Activating Token Index: 147

Text #4

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.6021. Min Act: -0.1700

Data Index: 5798853 (Open Web Text)

Max Activating Token Index: 917

Text #5

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.6080. Min Act: -0.1700

Data Index: 5716065 (Open Web Text)

Max Activating Token Index: 288

Text #6

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.5967. Min Act: -0.1700

Data Index: 1538744 (Open Web Text)

Max Activating Token Index: 892

Text #7

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.5680. Min Act: -0.1700

Data Index: 7419490 (Open Web Text)

Max Activating Token Index: 210

Text #8

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.5677. Min Act: -0.1700

Data Index: 8749251 (Open Web Text)

Max Activating Token Index: 565

Text #9

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.5623. Min Act: -0.1700

Data Index: 1160753 (Open Web Text)

Max Activating Token Index: 702

Text #10

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.5603. Min Act: -0.1700

Data Index: 2958957 (Open Web Text)

Max Activating Token Index: 1012

Text #11

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.5141. Min Act: -0.1700

Data Index: 577806 (Open Web Text)

Max Activating Token Index: 809

Text #12

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.5099. Min Act: -0.1700

Data Index: 7730391 (Open Web Text)

Max Activating Token Index: 329

Text #13

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.5355. Min Act: -0.1700

Data Index: 8339795 (Open Web Text)

Max Activating Token Index: 992

Text #14

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.5420. Min Act: -0.1700

Data Index: 4978172 (Open Web Text)

Max Activating Token Index: 606

Text #15

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.5192. Min Act: -0.1700

Data Index: 8608818 (Open Web Text)

Max Activating Token Index: 621

Text #16

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.5435. Min Act: -0.1700

Data Index: 1100839 (Open Web Text)

Max Activating Token Index: 410

Text #17

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.5256. Min Act: -0.1700

Data Index: 7164090 (Open Web Text)

Max Activating Token Index: 219

Text #18

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.4981. Min Act: -0.1700

Data Index: 715136 (Open Web Text)

Max Activating Token Index: 533

Text #19

Max Range: 4.6542. Min Range: -4.6542

Max Act: 4.4794. Min Act: -0.1700

Data Index: 5213174 (Open Web Text)

Max Activating Token Index: 288