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

Dataset: Open Web Text

Neuron 2676 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: 4.8892. Min Range: -4.8892

Max Act: 4.8892. Min Act: -0.1700

Data Index: 6502143 (Open Web Text)

Max Activating Token Index: 583

Text #1

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.7547. Min Act: -0.1700

Data Index: 4895469 (Open Web Text)

Max Activating Token Index: 374

Text #2

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.7502. Min Act: -0.1700

Data Index: 6931439 (Open Web Text)

Max Activating Token Index: 390

Text #3

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.6887. Min Act: -0.1700

Data Index: 1052516 (Open Web Text)

Max Activating Token Index: 539

Text #4

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.5774. Min Act: -0.1700

Data Index: 3127842 (Open Web Text)

Max Activating Token Index: 442

Text #5

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.5924. Min Act: -0.1700

Data Index: 2816744 (Open Web Text)

Max Activating Token Index: 191

Text #6

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.5876. Min Act: -0.1700

Data Index: 3127834 (Open Web Text)

Max Activating Token Index: 680

Text #7

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.5197. Min Act: -0.1700

Data Index: 4066241 (Open Web Text)

Max Activating Token Index: 763

Text #8

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.5623. Min Act: -0.1700

Data Index: 7211186 (Open Web Text)

Max Activating Token Index: 930

Text #9

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.5104. Min Act: -0.1700

Data Index: 3127850 (Open Web Text)

Max Activating Token Index: 206

Text #10

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.5207. Min Act: -0.1700

Data Index: 4008099 (Open Web Text)

Max Activating Token Index: 985

Text #11

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.5108. Min Act: -0.1700

Data Index: 247672 (Open Web Text)

Max Activating Token Index: 177

Text #12

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.5129. Min Act: -0.1700

Data Index: 1346749 (Open Web Text)

Max Activating Token Index: 489

Text #13

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.5055. Min Act: -0.1700

Data Index: 6165741 (Open Web Text)

Max Activating Token Index: 260

Text #14

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.4665. Min Act: -0.1700

Data Index: 2845689 (Open Web Text)

Max Activating Token Index: 986

Text #15

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.5093. Min Act: -0.1700

Data Index: 229815 (Open Web Text)

Max Activating Token Index: 662

Text #16

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.4946. Min Act: -0.1700

Data Index: 6459001 (Open Web Text)

Max Activating Token Index: 860

Text #17

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.4751. Min Act: -0.1700

Data Index: 1922443 (Open Web Text)

Max Activating Token Index: 1020

Text #18

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.4393. Min Act: -0.1700

Data Index: 5902573 (Open Web Text)

Max Activating Token Index: 211

Text #19

Max Range: 4.8892. Min Range: -4.8892

Max Act: 4.4725. Min Act: -0.1700

Data Index: 2611765 (Open Web Text)

Max Activating Token Index: 941