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

Dataset: Open Web Text

Neuron 168 in Layer 2

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: 4.4933. Min Range: -4.4933

Max Act: 4.4933. Min Act: -0.1700

Data Index: 1732567 (Open Web Text)

Max Activating Token Index: 84

Text #1

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.4581. Min Act: -0.1700

Data Index: 4891613 (Open Web Text)

Max Activating Token Index: 1017

Text #2

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.4330. Min Act: -0.1700

Data Index: 2582810 (Open Web Text)

Max Activating Token Index: 680

Text #3

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.4147. Min Act: -0.1700

Data Index: 6846342 (Open Web Text)

Max Activating Token Index: 390

Text #4

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.3935. Min Act: -0.1700

Data Index: 771154 (Open Web Text)

Max Activating Token Index: 699

Text #5

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.4199. Min Act: -0.1700

Data Index: 4901237 (Open Web Text)

Max Activating Token Index: 412

Text #6

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.4117. Min Act: -0.1700

Data Index: 2048017 (Open Web Text)

Max Activating Token Index: 552

Text #7

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.3841. Min Act: -0.1700

Data Index: 3519154 (Open Web Text)

Max Activating Token Index: 811

Text #8

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.3985. Min Act: -0.1700

Data Index: 631947 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.3939. Min Act: -0.1700

Data Index: 5659989 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.3848. Min Act: -0.1700

Data Index: 2920267 (Open Web Text)

Max Activating Token Index: 790

Text #11

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.3814. Min Act: -0.1700

Data Index: 1781157 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.3614. Min Act: -0.1700

Data Index: 214725 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.3810. Min Act: -0.1700

Data Index: 3682906 (Open Web Text)

Max Activating Token Index: 801

Text #14

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.3697. Min Act: -0.1700

Data Index: 2474757 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.3836. Min Act: -0.1700

Data Index: 177643 (Open Web Text)

Max Activating Token Index: 433

Text #16

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.3665. Min Act: -0.1700

Data Index: 1683985 (Open Web Text)

Max Activating Token Index: 636

Text #17

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.3828. Min Act: -0.1700

Data Index: 774465 (Open Web Text)

Max Activating Token Index: 391

Text #18

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.3818. Min Act: -0.1700

Data Index: 1604724 (Open Web Text)

Max Activating Token Index: 29

Text #19

Max Range: 4.4933. Min Range: -4.4933

Max Act: 4.3806. Min Act: -0.1700

Data Index: 2259400 (Open Web Text)

Max Activating Token Index: 2