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

Dataset: Open Web Text

Neuron 1639 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: 5.3282. Min Range: -5.3282

Max Act: 5.3282. Min Act: -0.1700

Data Index: 4895465 (Open Web Text)

Max Activating Token Index: 193

Text #1

Max Range: 5.3282. Min Range: -5.3282

Max Act: 5.2535. Min Act: -0.1700

Data Index: 4755600 (Open Web Text)

Max Activating Token Index: 938

Text #2

Max Range: 5.3282. Min Range: -5.3282

Max Act: 5.0912. Min Act: -0.1700

Data Index: 3721954 (Open Web Text)

Max Activating Token Index: 70

Text #3

Max Range: 5.3282. Min Range: -5.3282

Max Act: 5.0035. Min Act: -0.1700

Data Index: 2129530 (Open Web Text)

Max Activating Token Index: 621

Text #4

Max Range: 5.3282. Min Range: -5.3282

Max Act: 5.0091. Min Act: -0.1700

Data Index: 2012266 (Open Web Text)

Max Activating Token Index: 909

Text #5

Max Range: 5.3282. Min Range: -5.3282

Max Act: 4.9986. Min Act: -0.1700

Data Index: 7760830 (Open Web Text)

Max Activating Token Index: 286

Text #6

Max Range: 5.3282. Min Range: -5.3282

Max Act: 4.9546. Min Act: -0.1700

Data Index: 1060060 (Open Web Text)

Max Activating Token Index: 351

Text #7

Max Range: 5.3282. Min Range: -5.3282

Max Act: 4.9733. Min Act: -0.1700

Data Index: 202857 (Open Web Text)

Max Activating Token Index: 858

Text #8

Max Range: 5.3282. Min Range: -5.3282

Max Act: 4.9755. Min Act: -0.1700

Data Index: 4864895 (Open Web Text)

Max Activating Token Index: 1017

Text #9

Max Range: 5.3282. Min Range: -5.3282

Max Act: 4.9078. Min Act: -0.1700

Data Index: 7720783 (Open Web Text)

Max Activating Token Index: 910

Text #10

Max Range: 5.3282. Min Range: -5.3282

Max Act: 4.9132. Min Act: -0.1700

Data Index: 2218437 (Open Web Text)

Max Activating Token Index: 902

Text #11

Max Range: 5.3282. Min Range: -5.3282

Max Act: 4.9255. Min Act: -0.1700

Data Index: 1671779 (Open Web Text)

Max Activating Token Index: 246

Text #12

Max Range: 5.3282. Min Range: -5.3282

Max Act: 4.9156. Min Act: -0.1700

Data Index: 7003805 (Open Web Text)

Max Activating Token Index: 629

Text #13

Max Range: 5.3282. Min Range: -5.3282

Max Act: 4.9049. Min Act: -0.1700

Data Index: 7766678 (Open Web Text)

Max Activating Token Index: 410

Text #14

Max Range: 5.3282. Min Range: -5.3282

Max Act: 4.9996. Min Act: -0.1700

Data Index: 2012658 (Open Web Text)

Max Activating Token Index: 829

Text #15

Max Range: 5.3282. Min Range: -5.3282

Max Act: 4.9199. Min Act: -0.1700

Data Index: 2987995 (Open Web Text)

Max Activating Token Index: 253

Text #16

Max Range: 5.3282. Min Range: -5.3282

Max Act: 4.8673. Min Act: -0.1700

Data Index: 7902274 (Open Web Text)

Max Activating Token Index: 287

Text #17

Max Range: 5.3282. Min Range: -5.3282

Max Act: 4.8877. Min Act: -0.1700

Data Index: 8033340 (Open Web Text)

Max Activating Token Index: 384

Text #18

Max Range: 5.3282. Min Range: -5.3282

Max Act: 4.9041. Min Act: -0.1700

Data Index: 440187 (Open Web Text)

Max Activating Token Index: 1007

Text #19

Max Range: 5.3282. Min Range: -5.3282

Max Act: 4.8495. Min Act: -0.1700

Data Index: 5405638 (Open Web Text)

Max Activating Token Index: 625