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

Dataset: Open Web Text

Neuron 2365 in Layer 0

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: 1.5698. Min Range: -1.5698

Max Act: 1.5698. Min Act: 0.0367

Data Index: 4230004 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.5378. Min Act: -0.0522

Data Index: 7503340 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.5301. Min Act: -0.0505

Data Index: 7985954 (Open Web Text)

Max Activating Token Index: 1018

Text #3

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.5254. Min Act: -0.0373

Data Index: 850382 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.5140. Min Act: -0.0646

Data Index: 3872697 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.5109. Min Act: 0.0720

Data Index: 8270225 (Open Web Text)

Max Activating Token Index: 563

Text #6

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.5151. Min Act: -0.1298

Data Index: 3512811 (Open Web Text)

Max Activating Token Index: 1018

Text #7

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.5067. Min Act: -0.0843

Data Index: 7785204 (Open Web Text)

Max Activating Token Index: 1020

Text #8

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.5077. Min Act: -0.1359

Data Index: 6842121 (Open Web Text)

Max Activating Token Index: 1013

Text #9

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.5051. Min Act: -0.0651

Data Index: 1863902 (Open Web Text)

Max Activating Token Index: 1017

Text #10

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.5014. Min Act: -0.0651

Data Index: 8516277 (Open Web Text)

Max Activating Token Index: 1004

Text #11

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4930. Min Act: -0.0767

Data Index: 7303798 (Open Web Text)

Max Activating Token Index: 1018

Text #12

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4873. Min Act: -0.1583

Data Index: 2508393 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4934. Min Act: -0.0976

Data Index: 6398020 (Open Web Text)

Max Activating Token Index: 1011

Text #14

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4982. Min Act: -0.0585

Data Index: 53097 (Open Web Text)

Max Activating Token Index: 1014

Text #15

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4876. Min Act: -0.1651

Data Index: 3120667 (Open Web Text)

Max Activating Token Index: 1017

Text #16

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4864. Min Act: -0.1486

Data Index: 7058211 (Open Web Text)

Max Activating Token Index: 1017

Text #17

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4833. Min Act: -0.0779

Data Index: 7012187 (Open Web Text)

Max Activating Token Index: 1020

Text #18

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4849. Min Act: -0.0027

Data Index: 8124493 (Open Web Text)

Max Activating Token Index: 161

Text #19

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4841. Min Act: -0.0613

Data Index: 4697563 (Open Web Text)

Max Activating Token Index: 1020