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

Dataset: Open Web Text

Neuron 2750 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: 3.4981. Min Range: -3.4981

Max Act: 3.4981. Min Act: -0.1700

Data Index: 1161042 (Open Web Text)

Max Activating Token Index: 585

Text #1

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.4501. Min Act: -0.1700

Data Index: 2879526 (Open Web Text)

Max Activating Token Index: 684

Text #2

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.3906. Min Act: -0.1700

Data Index: 8137914 (Open Web Text)

Max Activating Token Index: 860

Text #3

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.3584. Min Act: -0.1700

Data Index: 4377642 (Open Web Text)

Max Activating Token Index: 474

Text #4

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.3471. Min Act: -0.1700

Data Index: 6595001 (Open Web Text)

Max Activating Token Index: 377

Text #5

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.3423. Min Act: -0.1700

Data Index: 6387626 (Open Web Text)

Max Activating Token Index: 963

Text #6

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.3330. Min Act: -0.1700

Data Index: 5666753 (Open Web Text)

Max Activating Token Index: 623

Text #7

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.3208. Min Act: -0.1700

Data Index: 4240181 (Open Web Text)

Max Activating Token Index: 314

Text #8

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.3058. Min Act: -0.1700

Data Index: 8596762 (Open Web Text)

Max Activating Token Index: 123

Text #9

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.3018. Min Act: -0.1700

Data Index: 6678411 (Open Web Text)

Max Activating Token Index: 151

Text #10

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.2834. Min Act: -0.1700

Data Index: 3821748 (Open Web Text)

Max Activating Token Index: 214

Text #11

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.2788. Min Act: -0.1700

Data Index: 8027017 (Open Web Text)

Max Activating Token Index: 381

Text #12

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.2782. Min Act: -0.1700

Data Index: 6577008 (Open Web Text)

Max Activating Token Index: 172

Text #13

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.2710. Min Act: -0.1700

Data Index: 4740718 (Open Web Text)

Max Activating Token Index: 365

Text #14

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.2484. Min Act: -0.1700

Data Index: 1812108 (Open Web Text)

Max Activating Token Index: 461

Text #15

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.2360. Min Act: -0.1700

Data Index: 6492099 (Open Web Text)

Max Activating Token Index: 583

Text #16

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.2230. Min Act: -0.1700

Data Index: 4596174 (Open Web Text)

Max Activating Token Index: 611

Text #17

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.2206. Min Act: -0.1700

Data Index: 6502559 (Open Web Text)

Max Activating Token Index: 76

Text #18

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.2118. Min Act: -0.1700

Data Index: 6567430 (Open Web Text)

Max Activating Token Index: 588

Text #19

Max Range: 3.4981. Min Range: -3.4981

Max Act: 3.2192. Min Act: -0.1700

Data Index: 8567647 (Open Web Text)

Max Activating Token Index: 1017